Article(id=1209816725265183104, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405631, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1721923200000, receivedDateStr=2024-07-26, revisedDate=1734883200000, revisedDateStr=2024-12-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1766372384610, onlineDateStr=2025-12-22, pubDate=1751904000000, pubDateStr=2025-07-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766372384610, onlineIssueDateStr=2025-12-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766372384610, creator=13701087609, updateTime=1766372384610, updator=13701087609, issue=Issue{id=1209811339510411616, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='19', pageStart='7885', pageEnd='8315', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1766371100547, creator=13701087609, updateTime=1766373228996, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1209820266960654935, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1209820266960654936, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=8158, endPage=8166, ext={EN=ArticleExt(id=1209816725693002115, articleId=1209816725265183104, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Automatic Matching Technology of Anti-counterfeiting Feature Extraction Algorithm Based on Microscopic Vision and Neural Network, columnId=1209816719539966141, journalTitle=Science Technology and Engineering, columnName=Papers∙Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

Aiming at the limitations of current intelligent traceability and authenticity identification systems in extracting multiple surface texture features (such as continuous, non-continuous, etc.) of automotive components, a micro-visual and neural network-based automotive parts anti-counterfeiting feature extraction and automatic matching algorithm was proposed. This algorithm integrated artificial intelligence-based automatic matching technology with micro-visual image processing and a neural network hybrid algorithm for anti-counterfeiting feature extraction and identification of automotive parts. Initially, the micro-visual feature images of the automotive component surfaces were processed with frequency-domain transformation, filtering, and noise reduction. Subsequently, the texture types (including continuous, non-continuous, and contour types) were determined based on the two-dimensional frequency-domain features. For each texture type, an appropriate algorithm was selected from the algorithm library to extract and analyze key attribute feature points. Finally, a deep learning framework was constructed, and a micro-visual feature recognition model for automotive parts was built, which was then matched with a priori feature libraries to complete classification and authenticity determination. Experimental results demonstrate that the proposed algorithm effectively extracts and identifies anti-counterfeiting features on the surface of automotive components, achieving a significant improvement in accuracy compared to traditional methods. Through matching with the a priori feature library, the algorithm accurately distinguishes between genuine and counterfeit components, providing reliable anti-counterfeiting verification results. This method effectively addresses the complexity of extracting various surface texture features of automotive parts, enhancing the accuracy of anti-counterfeiting and traceability systems. The micro-visual and neural network-based automatic matching technology significantly improves the precision of authenticity identification, offering an innovative and efficient solution for automotive parts anti-counterfeiting.

, correspAuthors=Jing FANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Ying HONG, Bo YANG, Jia-cai HUANG, Peng-fei JIANG, Ruo-han HOU, Jin-ling WANG, Jing FANG), CN=ArticleExt(id=1209816727790154140, articleId=1209816725265183104, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术, columnId=1209816721498706113, journalTitle=科学技术与工程, columnName=论文∙自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

针对当前汽车零部件多特征提取智能溯源与真伪鉴别系统在提取多种汽车零部件材料表面纹理(如连续型、非连续型等)特征时存在的局限性,提出一种基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术。该算法结合人工智能自动匹配技术与微观视觉图像处理及神经网络混合算法,对汽车零部件进行防伪特征提取与识别。首先对采集的汽车零部件材料表面微观视觉特征图像进行频域变换、滤波和降噪处理;然后根据二维频域特征判断纹理类型(包括连续型、非连续型和轮廓型);针对不同纹理类型,从算法库中选择适合的算法,提取并分析关键属性特征点。最后,构建深度学习框架,搭建汽车零部件微观视觉特征识别模型,并与先验特征库进行匹配,完成分类与真伪判定。实验结果表明,该算法能够有效提取并识别汽车零部件表面的防伪特征,准确率较传统方法有显著提升。通过与先验特征库的匹配,算法能够准确区分真伪,提供可靠的防伪验证结果。该方法能够有效解决多种汽车零部件材料表面纹理特征提取的复杂性,提升了防伪和溯源系统的准确性。基于微观视觉和神经网络的自动匹配技术显著增强了汽车零部件真伪鉴别的精确度,为汽车零部件的防伪提供了一种创新且高效的解决方案。

, correspAuthors=方静, authorNote=null, correspAuthorsNote=
*方静(1987—),女,汉族,江苏无锡人,硕士,工程师。研究方向:汽车零部件多特征识别等。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=NUufSt0P7TdkGA/RA33zKA==, magXml=e1hywJvkIj4vFyXgaAKnYg==, pdfUrl=null, pdf=JZ4kldB+MauHU5Ph38WlaQ==, pdfFileSize=10736198, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=tC1oz8EYbj1z6XEa7q6fkA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Fp+GPRvpGlzuCWZcV1BhTg==, mapNumber=null, authorCompany=null, fund=null, authors=

洪颖(1980—),女,汉族,江苏南京人,博士,研究员。研究方向:汽车零部件多特征识别和区块链溯源等。E-mail:

, authorsList=洪颖, 杨博, 黄家才, 江鹏飞, 侯若涵, 王金陵, 方静)}, authors=[Author(id=1209885575688090209, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hongy@njjszx.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885575767781991, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885575688090209, language=EN, stringName=Ying HONG, firstName=Ying, middleName=null, lastName=HONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885575864250987, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885575688090209, language=CN, stringName=洪颖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 南京海关工业产品检测中心, 南京 210005, bio={"content":"

洪颖(1980—),女,汉族,江苏南京人,博士,研究员。研究方向:汽车零部件多特征识别和区块链溯源等。E-mail:

"}, bioImg=null, bioContent=

洪颖(1980—),女,汉族,江苏南京人,博士,研究员。研究方向:汽车零部件多特征识别和区块链溯源等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575256076870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=1, ext=[AuthorCompanyExt(id=1209885575264465478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China), AuthorCompanyExt(id=1209885575272854087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京海关工业产品检测中心, 南京 210005)])]), Author(id=1209885575927165551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885575998468724, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885575927165551, language=EN, stringName=Bo YANG, firstName=Bo, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Communication and information engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885576065577591, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885575927165551, language=CN, stringName=杨博, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 南京邮电大学通信与信息工程学院, 南京 210003, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575390294601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=2, ext=[AuthorCompanyExt(id=1209885575398683211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575390294601, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Communication and information engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China), AuthorCompanyExt(id=1209885575407071820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575390294601, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南京邮电大学通信与信息工程学院, 南京 210003)])]), Author(id=1209885576141075068, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885576224961155, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576141075068, language=EN, stringName=Jia-cai HUANG, firstName=Jia-cai, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 College of Mechanical Engineering, Nanjing Institute of Technology, Nanjing 211167, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885576283681416, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576141075068, language=CN, stringName=黄家才, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 南京工程学院机械工程学院, 南京 211167, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575486763599, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=3, ext=[AuthorCompanyExt(id=1209885575499346512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575486763599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 College of Mechanical Engineering, Nanjing Institute of Technology, Nanjing 211167, China), AuthorCompanyExt(id=1209885575507735121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575486763599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 南京工程学院机械工程学院, 南京 211167)])]), Author(id=1209885576346595980, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885576451453585, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576346595980, language=EN, stringName=Peng-fei JIANG, firstName=Peng-fei, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 Nanchang Customs Technology Center, Nanchang 330038, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885576547922583, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576346595980, language=CN, stringName=江鹏飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 南昌海关技术中心, 南昌 330038, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575591621208, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=4, ext=[AuthorCompanyExt(id=1209885575595815513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575591621208, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Nanchang Customs Technology Center, Nanchang 330038, China), AuthorCompanyExt(id=1209885575604204122, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575591621208, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 南昌海关技术中心, 南昌 330038)])]), Author(id=1209885576648585884, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885576761832097, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576648585884, language=EN, stringName=Ruo-han HOU, firstName=Ruo-han, middleName=null, lastName=HOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Communication and information engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885576870884005, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576648585884, language=CN, stringName=侯若涵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 南京邮电大学通信与信息工程学院, 南京 210003, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575390294601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=2, ext=[AuthorCompanyExt(id=1209885575398683211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575390294601, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Communication and information engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China), AuthorCompanyExt(id=1209885575407071820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575390294601, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南京邮电大学通信与信息工程学院, 南京 210003)])]), Author(id=1209885576963158701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885577080599222, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576963158701, language=EN, stringName=Jin-ling WANG, firstName=Jin-ling, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885577151902397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885576963158701, language=CN, stringName=王金陵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 南京海关工业产品检测中心, 南京 210005, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575256076870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=1, ext=[AuthorCompanyExt(id=1209885575264465478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China), AuthorCompanyExt(id=1209885575272854087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京海关工业产品检测中心, 南京 210005)])]), Author(id=1209885577227399875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fangj@njjszx.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1209885577336451789, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885577227399875, language=EN, stringName=Jing FANG, firstName=Jing, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885577416143572, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, authorId=1209885577227399875, language=CN, stringName=方静, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 南京海关工业产品检测中心, 南京 210005, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885575256076870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=1, ext=[AuthorCompanyExt(id=1209885575264465478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China), AuthorCompanyExt(id=1209885575272854087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京海关工业产品检测中心, 南京 210005)])])], keywords=[Keyword(id=1209885577583915745, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, orderNo=1, keyword=feature extraction), Keyword(id=1209885577680384745, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, orderNo=2, keyword=micro image processing), Keyword(id=1209885577751687919, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, orderNo=3, keyword=neural network), Keyword(id=1209885577831379702, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, orderNo=4, keyword=automatic matching), Keyword(id=1209885577927848702, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, orderNo=5, keyword=micro visual), Keyword(id=1209885577994957571, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, orderNo=1, keyword=特征提取), Keyword(id=1209885578087232268, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, orderNo=2, keyword=微观图像处理), Keyword(id=1209885578162729743, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, orderNo=3, keyword=神经网络), Keyword(id=1209885578229838615, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, orderNo=4, keyword=自动匹配), Keyword(id=1209885578347279136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, orderNo=5, keyword=微观视觉)], refs=[Reference(id=1209885579517490030, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=袁纵青, journalName=基于机器视觉的汽车零部件字符检测系统设计与实现, refType=null, unstructuredReference=袁纵青. 基于机器视觉的汽车零部件字符检测系统设计与实现[D]. 徐州: 中国矿业大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1209885579664290679, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Yuan Zongqing, journalName=Design and implementation of character detection system for auto parts based on machine vision, refType=null, unstructuredReference=Yuan Zongqing. Design and implementation of character detection system for auto parts based on machine vision[D]. Xuzhou: China University of Mining and Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1209885579785925498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2022, volume=5, issue=11, pageStart=18, pageEnd=27, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Hang D, Jing J, journalName=Academic Journal of Computing Information Science, refType=null, unstructuredReference=Hang D, Jing J. Wireless sensor network physical layer authentication technology based on dynamic prediction of electromagnetic fingerprints[J]. Academic Journal of Computing Information Science, 2022, 5(11): 18-27., articleTitle=Wireless sensor network physical layer authentication technology based on dynamic prediction of electromagnetic fingerprints, refAbstract=null), Reference(id=1209885579865617281, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2010, volume=6, issue=22, pageStart=6309, pageEnd=6310, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=赵玉兰, journalName=电脑知识与技术, refType=null, unstructuredReference=赵玉兰. 基于纹理结构的指纹匹配算法的研究与应用[J]. 电脑知识与技术, 2010, 6(22): 6309-6310., articleTitle=基于纹理结构的指纹匹配算法的研究与应用, refAbstract=null), Reference(id=1209885579970474884, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2010, volume=6, issue=22, pageStart=6309, pageEnd=6310, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhao Yulan, journalName=Computer Konwledge and Technology, refType=null, unstructuredReference=Zhao Yulan. Research and application of fingerprint matching algorithm based on texture structure[J]. Computer Konwledge and Technology, 2010, 6(22): 6309-6310., articleTitle=Research and application of fingerprint matching algorithm based on texture structure, refAbstract=null), Reference(id=1209885580050166665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=施佺, journalName=null, refType=null, unstructuredReference=施佺. 基于灰度的分布式图像底层特征识别方法及系统: CN201510671757.8[P]. 2016-02-24., articleTitle=null, refAbstract=null), Reference(id=1209885580121469840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Shi Quan, journalName=null, refType=null, unstructuredReference=Shi Quan. Method and system of distributed image bottom feature recognition based on gray scale: CN201510671757.8[P]. 2016-02-24., articleTitle=null, refAbstract=null), Reference(id=1209885580217938834, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=16, pageStart=6917, pageEnd=6922, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=徐佳楠, 张天瑞, 李玉龙, journalName=科学技术与工程, refType=null, unstructuredReference=徐佳楠, 张天瑞, 李玉龙. 基于自适应遗传-粒子群优化算法的风电场微观选址优化[J]. 科学技术与工程, 2023, 23(16): 6917-6922., articleTitle=基于自适应遗传-粒子群优化算法的风电场微观选址优化, refAbstract=null), Reference(id=1209885580297630619, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=16, pageStart=6917, pageEnd=6922, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Xu Jiannan, Zhang Tianrui, Li Yulong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Xu Jiannan, Zhang Tianrui, Li Yulong. Micro-location and optimization of wind farm based on the adaptive GA-PSO algorithm[J]. Science Technology and Engineering, 2023, 23(16): 6917-6922., articleTitle=Micro-location and optimization of wind farm based on the adaptive GA-PSO algorithm, refAbstract=null), Reference(id=1209885580373128096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=1625, pageEnd=1634, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=王莉, 任健荣, 王涛, journalName=科学技术与工程, refType=null, unstructuredReference=王莉, 任健荣, 王涛, 等. 基于区块链的粮食防伪溯源系统的设计与实现[J]. 科学技术与工程, 2023, 23(4): 1625-1634., articleTitle=基于区块链的粮食防伪溯源系统的设计与实现, refAbstract=null), Reference(id=1209885580473791401, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=1625, pageEnd=1634, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Wang Li, Ren Jianrong, Wang Tao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Li, Ren Jianrong, Wang Tao, et al. Design and implementation of food security traceability system based on blockchain[J]. Science Technology and Engineering, 2023, 23(4): 1625-1634., articleTitle=Design and implementation of food security traceability system based on blockchain, refAbstract=null), Reference(id=1209885580557677486, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=35, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=洪坤明, 刘新亮, 高圣乔, journalName=科学技术与工程, refType=null, unstructuredReference=洪坤明, 刘新亮, 高圣乔. 基于联盟区块链的水产养殖品质量追溯系统的设计与实现[J]. 科学技术与工程, 2019, 19 (35): 79-86., articleTitle=基于联盟区块链的水产养殖品质量追溯系统的设计与实现, refAbstract=null), Reference(id=1209885580654146483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=35, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Hong Kunming, Liu Xinliang, Gao Shengqiao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Hong Kunming, Liu Xinliang, Gao Shengqiao. Design and implementation of traceability system for aquaculture products based on coalition block chain[J]. Science Technology and Engineering, 2019, 19(35): 79-86., articleTitle=Design and implementation of traceability system for aquaculture products based on coalition block chain, refAbstract=null), Reference(id=1209885580754809787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=4, pageStart=1, pageEnd=16, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Li T, Chen H, Yuan J, journalName=Discrete Dynamics in Nature and Soeiety, refType=null, unstructuredReference=Li T, Chen H, Yuan J, et al. Quality risk propagation of complex product collaborative manutacturing supply chain network based on CN and SoV[J]. Discrete Dynamics in Nature and Soeiety, 2020(4): 1-16., articleTitle=Quality risk propagation of complex product collaborative manutacturing supply chain network based on CN and SoV, refAbstract=null), Reference(id=1209885580884833216, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2018, volume=15, issue=2, pageStart=1120, pageEnd=1130, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=Wang N, Yu Q, Wan H, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=Wang N, Yu Q, Wan H, et a1. Adaptive scheduling for multi-cluster time—triggered train communication networks[J]. IEEE Transactions on Industrial Informatics, 2018, 15(2): 1120-1130., articleTitle=et a1. Adaptive scheduling for multi-cluster time—triggered train communication networks, refAbstract=null), Reference(id=1209885580964524996, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=153, issue=null, pageStart=110563, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=Fan L, Yan X, Li H, journalName=Pattern Recognition, refType=null, unstructuredReference=Fan L, Yan X, Li H, et al. Bidirectional image denoising with blurred image feature[J]. Pattern Recognition, 2024, 153: 110563., articleTitle=Bidirectional image denoising with blurred image feature, refAbstract=null), Reference(id=1209885581065188298, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=125, issue=null, pageStart=117134, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Das D, Naskar R, journalName=Signal Processing: Image Communication, refType=null, unstructuredReference=Das D, Naskar R. Image splicing detection using low-dimensional feature vector of texture features and Haralick features based on gray level co-occurrence matrix[J]. Signal Processing: Image Communication, 2024, 125: 117134., articleTitle=Image splicing detection using low-dimensional feature vector of texture features and Haralick features based on gray level co-occurrence matrix, refAbstract=null), Reference(id=1209885581186823125, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=4, pageStart=369, pageEnd=376, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Shubhra P, Bhojan R, journalName=International Journal of Electrical and Computer Engineering Systems, refType=null, unstructuredReference=Shubhra P, Bhojan R. Gray level co-occurrence matrix based fully convolutional neural network model for pneumonia detection[J]. International Journal of Electrical and Computer Engineering Systems, 2024, 15(4): 369-376., articleTitle=Gray level co-occurrence matrix based fully convolutional neural network model for pneumonia detection, refAbstract=null), Reference(id=1209885581274903513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=7, pageStart=2956, pageEnd=2965, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=韩虎, 吕宪勇, 李云霞, journalName=科学技术与工程, refType=null, unstructuredReference=韩虎, 吕宪勇, 李云霞, 等. 基于可视化分析模型的汽车电控系统需求开发方法[J]. 科学技术与工程, 2024, 24(7): 2956-2965., articleTitle=基于可视化分析模型的汽车电控系统需求开发方法, refAbstract=null), Reference(id=1209885581358789601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=7, pageStart=2956, pageEnd=2965, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=Han Hu, Lü Xianyong, Li Yunxia, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Han Hu, Xianyong, Li Yunxia, et al. Requirements development method of automotive electronic control system based on visual analysis model[J]. Science Technology and Engineering, 2024, 24(7): 2956-2965., articleTitle=Requirements development method of automotive electronic control system based on visual analysis model, refAbstract=null), Reference(id=1209885581434287078, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=42, issue=2, pageStart=226, pageEnd=232, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=唐嘉男, 孟祥瑞, journalName=湖北民族大学学报(自然科学版), refType=null, unstructuredReference=唐嘉男, 孟祥瑞. 基于多尺度信息提取和特征融合的皮肤镜图像分割算法[J]. 湖北民族大学学报(自然科学版), 2024, 42(2): 226-232., articleTitle=基于多尺度信息提取和特征融合的皮肤镜图像分割算法, refAbstract=null), Reference(id=1209885581610447853, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=42, issue=2, pageStart=226, pageEnd=232, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=Tang Jianan, Meng Xiangrui, journalName=Journal of Hubei Minzu University (Nature Science Edition), refType=null, unstructuredReference=Tang Jianan, Meng Xiangrui. Dermoscopic image segmentation algorithm based on multi-scale information extraction and feature fusion[J]. Journal of Hubei Minzu University (Nature Science Edition), 2024, 42(2): 226-232., articleTitle=Dermoscopic image segmentation algorithm based on multi-scale information extraction and feature fusion, refAbstract=null), Reference(id=1209885581694333938, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2018, volume=35, issue=6, pageStart=309, pageEnd=312, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=李云飞, 刘菊琨, 柳青, journalName=计算机应用与软件, refType=null, unstructuredReference=李云飞, 刘菊琨, 柳青. 改进RSA算法的安全性分析[J]. 计算机应用与软件, 2018, 35(6): 309-312., articleTitle=改进RSA算法的安全性分析, refAbstract=null), Reference(id=1209885581778220023, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2018, volume=35, issue=6, pageStart=309, pageEnd=312, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=Li Yunfei, Liu Jukun, Liu Qing, journalName=Computer Applications and Software, refType=null, unstructuredReference=Li Yunfei, Liu Jukun, Liu Qing. Improved RSA algorithm security analysis[J]. Computer Applications and Software, 2018, 35(6): 309-312., articleTitle=Improved RSA algorithm security analysis, refAbstract=null), Reference(id=1209885581891466239, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=1, pageStart=16, pageEnd=20, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=赵维, journalName=技术经济与管理研究, refType=null, unstructuredReference=赵维. 基于区块链技术的农业食品安全追溯体系研究[J]. 技术经济与管理研究, 2019(1): 16-20., articleTitle=基于区块链技术的农业食品安全追溯体系研究, refAbstract=null), Reference(id=1209885582004711431, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=1, pageStart=16, pageEnd=20, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=Zhao Wei, journalName=Journal of Technical Economics & Management, refType=null, unstructuredReference=Zhao Wei. Research on traceability system of agricultural-food safety based on block chain technology[J]. Journal of Technical Economics & Management, 2019(1): 16-20., articleTitle=Research on traceability system of agricultural-food safety based on block chain technology, refAbstract=null), Reference(id=1209885582076014604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=10, pageStart=2409, pageEnd=2424, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=孟超, 周倩, 郭林, journalName=电子学报, refType=null, unstructuredReference=孟超, 周倩, 郭林, 等. 基于相关件传输模型的无线链路质量估计方法及路由优化算法[J]. 电子学报, 2022, 50(10): 2409-2424., articleTitle=基于相关件传输模型的无线链路质量估计方法及路由优化算法, refAbstract=null), Reference(id=1209885582147317775, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=10, pageStart=2409, pageEnd=2424, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=Meng Chao, Zhou Qian, Guo Lin, journalName=Acta Electronica Siniea, refType=null, unstructuredReference=Meng Chao, Zhou Qian, Guo Lin, et al. Estimation method of wireless link quality and routing optimization algorithm based on correlation transnlission model[J]. Acta Electronica Siniea, 2022, 50(10): 2409-2424., articleTitle=Estimation method of wireless link quality and routing optimization algorithm based on correlation transnlission model, refAbstract=null), Reference(id=1209885582256369685, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=178, issue=null, pageStart=106405, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=Fei M, Shen Z, Song Z, journalName=Neural Networks, refType=null, unstructuredReference=Fei M, Shen Z, Song Z, et al. Distillation of multi-class cervical lesion cell detection via synthesis-aided pre-training and patch-level feature alignment[J]. Neural Networks, 2024, 178: 106405., articleTitle=Distillation of multi-class cervical lesion cell detection via synthesis-aided pre-training and patch-level feature alignment, refAbstract=null), Reference(id=1209885582411558938, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=33, issue=null, pageStart=101223, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=Xu J, journalName=Measurement: Sensors, refType=null, unstructuredReference=Xu J. Image data visualization and communication system based on sensor network simulation and visual feature extraction[J]. Measurement: Sensors, 2024, 33: 101223., articleTitle=Image data visualization and communication system based on sensor network simulation and visual feature extraction, refAbstract=null), Reference(id=1209885582516416546, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=110, issue=null, pageStart=102455, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=30, authorNames=Zhang H, Wan J, He Z, journalName=Information Fusion, refType=null, unstructuredReference=Zhang H, Wan J, He Z, et al. Sparse agent transformer for unified voxel and image feature extraction and fusion[J]. Information Fusion, 2024, 110: 102455., articleTitle=Sparse agent transformer for unified voxel and image feature extraction and fusion, refAbstract=null), Reference(id=1209885582638051369, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=36, issue=18, pageStart=11033, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=31, authorNames=Aysun S, Basri H S, Songul A, journalName=Neural Computing and Applications, refType=null, unstructuredReference=Aysun S, Basri H S, Songul A. Retraction note: hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images[J]. Neural Computing and Applications, 2024, 36 (18): 11033., articleTitle=Retraction note: hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images, refAbstract=null), Reference(id=1209885582742908972, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=7, pageStart=5907, pageEnd=5930, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=Ahmed J B, Jiang G, Ziaur R, journalName=Applied Intelligence, refType=null, unstructuredReference=Ahmed J B, Jiang G, Ziaur R, et al. Feature extraction of multimodal medical image fusion using novel deep learning and contrast enhancement method[J]. Applied Intelligence, 2024, 54(7): 5907-5930., articleTitle=Feature extraction of multimodal medical image fusion using novel deep learning and contrast enhancement method, refAbstract=null)], funds=[Fund(id=1209885579228083036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, awardId=2024KJ07, language=CN, fundingSource=海关总署科研项目(2024KJ07), fundOrder=null, country=null), Fund(id=1209885579311969125, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, awardId=2024HK063, language=CN, fundingSource=海关总署科研项目(2024HK063), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1209885575256076870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=1, ext=[AuthorCompanyExt(id=1209885575264465478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China), AuthorCompanyExt(id=1209885575272854087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575256076870, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京海关工业产品检测中心, 南京 210005)]), AuthorCompany(id=1209885575390294601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=2, ext=[AuthorCompanyExt(id=1209885575398683211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575390294601, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Communication and information engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China), AuthorCompanyExt(id=1209885575407071820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575390294601, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南京邮电大学通信与信息工程学院, 南京 210003)]), AuthorCompany(id=1209885575486763599, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=3, ext=[AuthorCompanyExt(id=1209885575499346512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575486763599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 College of Mechanical Engineering, Nanjing Institute of Technology, Nanjing 211167, China), AuthorCompanyExt(id=1209885575507735121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575486763599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 南京工程学院机械工程学院, 南京 211167)]), AuthorCompany(id=1209885575591621208, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, xref=4, ext=[AuthorCompanyExt(id=1209885575595815513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575591621208, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Nanchang Customs Technology Center, Nanchang 330038, China), AuthorCompanyExt(id=1209885575604204122, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, companyId=1209885575591621208, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 南昌海关技术中心, 南昌 330038)])], figs=[ArticleFig(id=1209885578556994352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, label=Fig.1, caption=Comparison of micro feature images of genuine and fake automotive ceramic brake pads, figureFileSmall=abo8fDYA3vjG0h2ivPedrg==, figureFileBig=lZvAjVPipwe04dCuL0V5iw==, tableContent=null), ArticleFig(id=1209885578636686136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, label=图1, caption=真伪汽车陶瓷刹车片产品微观特征图像对比, figureFileSmall=abo8fDYA3vjG0h2ivPedrg==, figureFileBig=lZvAjVPipwe04dCuL0V5iw==, tableContent=null), ArticleFig(id=1209885578737349438, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, label=Fig.2, caption=Experimental results of enhancement of microscopic feature images of authentic and fake automotive ceramic brake pads, figureFileSmall=nIl6UT3rUj5EJypJerNV+Q==, figureFileBig=cINuRjG/fdlyvPZJN15Cjg==, tableContent=null), ArticleFig(id=1209885578858984262, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, label=图2, caption=真伪汽车陶瓷刹车片产品微观特征图像增强实验结果, figureFileSmall=nIl6UT3rUj5EJypJerNV+Q==, figureFileBig=cINuRjG/fdlyvPZJN15Cjg==, tableContent=null), ArticleFig(id=1209885578934481742, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=EN, label=Fig.3, caption=Comparative analysis of feature parameter extraction results of real and fake automobile ceramic brake pads microscopic feature images, figureFileSmall=gCVoBXi4qadJTGHuZAW4rQ==, figureFileBig=6mQ1br7L+GbWlwlU8u2eUw==, tableContent=null), ArticleFig(id=1209885579043533649, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816725265183104, language=CN, label=图3, caption=真伪汽车陶瓷刹车片微观特征图像特征参数提取结果对比分析, figureFileSmall=gCVoBXi4qadJTGHuZAW4rQ==, figureFileBig=6mQ1br7L+GbWlwlU8u2eUw==, tableContent=null)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405631, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405631, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405631, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405631, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术
收藏切换
PDF下载
洪颖 1 , 杨博 2 , 黄家才 3 , 江鹏飞 4 , 侯若涵 2 , 王金陵 1 , 方静 1, *
科学技术与工程 | 论文∙自动化技术、计算机技术 2025,25(19): 8158-8166
收起
收藏切换
科学技术与工程 | 论文∙自动化技术、计算机技术 2025, 25(19): 8158-8166
基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术
全屏
洪颖1 , 杨博2, 黄家才3, 江鹏飞4, 侯若涵2, 王金陵1, 方静1, *
作者信息
  • 1 南京海关工业产品检测中心, 南京 210005
  • 2 南京邮电大学通信与信息工程学院, 南京 210003
  • 3 南京工程学院机械工程学院, 南京 211167
  • 4 南昌海关技术中心, 南昌 330038
  • 洪颖(1980—),女,汉族,江苏南京人,博士,研究员。研究方向:汽车零部件多特征识别和区块链溯源等。E-mail:

通讯作者:

*方静(1987—),女,汉族,江苏无锡人,硕士,工程师。研究方向:汽车零部件多特征识别等。E-mail:
Automatic Matching Technology of Anti-counterfeiting Feature Extraction Algorithm Based on Microscopic Vision and Neural Network
Ying HONG1 , Bo YANG2, Jia-cai HUANG3, Peng-fei JIANG4, Ruo-han HOU2, Jin-ling WANG1, Jing FANG1, *
Affiliations
  • 1 Nanjing Customs District Industrial Products Inspeetion Center, Nanjing 210005, China
  • 2 College of Communication and information engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • 3 College of Mechanical Engineering, Nanjing Institute of Technology, Nanjing 211167, China
  • 4 Nanchang Customs Technology Center, Nanchang 330038, China
出版时间: 2025-07-08 doi: 10.12404/j.issn.1671-1815.2405631
文章导航
收藏切换

针对当前汽车零部件多特征提取智能溯源与真伪鉴别系统在提取多种汽车零部件材料表面纹理(如连续型、非连续型等)特征时存在的局限性,提出一种基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术。该算法结合人工智能自动匹配技术与微观视觉图像处理及神经网络混合算法,对汽车零部件进行防伪特征提取与识别。首先对采集的汽车零部件材料表面微观视觉特征图像进行频域变换、滤波和降噪处理;然后根据二维频域特征判断纹理类型(包括连续型、非连续型和轮廓型);针对不同纹理类型,从算法库中选择适合的算法,提取并分析关键属性特征点。最后,构建深度学习框架,搭建汽车零部件微观视觉特征识别模型,并与先验特征库进行匹配,完成分类与真伪判定。实验结果表明,该算法能够有效提取并识别汽车零部件表面的防伪特征,准确率较传统方法有显著提升。通过与先验特征库的匹配,算法能够准确区分真伪,提供可靠的防伪验证结果。该方法能够有效解决多种汽车零部件材料表面纹理特征提取的复杂性,提升了防伪和溯源系统的准确性。基于微观视觉和神经网络的自动匹配技术显著增强了汽车零部件真伪鉴别的精确度,为汽车零部件的防伪提供了一种创新且高效的解决方案。

特征提取  /  微观图像处理  /  神经网络  /  自动匹配  /  微观视觉

Aiming at the limitations of current intelligent traceability and authenticity identification systems in extracting multiple surface texture features (such as continuous, non-continuous, etc.) of automotive components, a micro-visual and neural network-based automotive parts anti-counterfeiting feature extraction and automatic matching algorithm was proposed. This algorithm integrated artificial intelligence-based automatic matching technology with micro-visual image processing and a neural network hybrid algorithm for anti-counterfeiting feature extraction and identification of automotive parts. Initially, the micro-visual feature images of the automotive component surfaces were processed with frequency-domain transformation, filtering, and noise reduction. Subsequently, the texture types (including continuous, non-continuous, and contour types) were determined based on the two-dimensional frequency-domain features. For each texture type, an appropriate algorithm was selected from the algorithm library to extract and analyze key attribute feature points. Finally, a deep learning framework was constructed, and a micro-visual feature recognition model for automotive parts was built, which was then matched with a priori feature libraries to complete classification and authenticity determination. Experimental results demonstrate that the proposed algorithm effectively extracts and identifies anti-counterfeiting features on the surface of automotive components, achieving a significant improvement in accuracy compared to traditional methods. Through matching with the a priori feature library, the algorithm accurately distinguishes between genuine and counterfeit components, providing reliable anti-counterfeiting verification results. This method effectively addresses the complexity of extracting various surface texture features of automotive parts, enhancing the accuracy of anti-counterfeiting and traceability systems. The micro-visual and neural network-based automatic matching technology significantly improves the precision of authenticity identification, offering an innovative and efficient solution for automotive parts anti-counterfeiting.

feature extraction  /  micro image processing  /  neural network  /  automatic matching  /  micro visual
洪颖, 杨博, 黄家才, 江鹏飞, 侯若涵, 王金陵, 方静. 基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术. 科学技术与工程, 2025 , 25 (19) : 8158 -8166 . DOI: 10.12404/j.issn.1671-1815.2405631
Ying HONG, Bo YANG, Jia-cai HUANG, Peng-fei JIANG, Ruo-han HOU, Jin-ling WANG, Jing FANG. Automatic Matching Technology of Anti-counterfeiting Feature Extraction Algorithm Based on Microscopic Vision and Neural Network[J]. Science Technology and Engineering, 2025 , 25 (19) : 8158 -8166 . DOI: 10.12404/j.issn.1671-1815.2405631
汽车零部件的防伪特征提取在汽车零部件多特征提取智能溯源与真伪鉴别系统中起到关键的作用,可以在对汽车零部件产品的真伪鉴别中提供有力的证据支撑。图像纹理特征提取技术作为计算机视觉和图像处理中的一个重要步骤,主要通过图像提取出有用的纹理信息,以便于后续的图像识别、分类和分析。有助于排除干扰因素,突出特征信息以改善计算机视觉的可靠性、提高汽车零部件目标检测与识别的准确性,并促进相关领域的发展和创新。因此,针对于图像纹理特征提取技术的研究对于实现更广泛的图像应用和推动科学技术进步具有重要意义。
目前对于汽车零部件等相关应用场景中的图像纹理特征提取技术研究诸多,如2020年,袁纵青[1]在《汽车零部件多特征提取智能溯源与真伪鉴别系统关键技术研究》中提出通过对零件表面压印字符进行分析,使用方向梯度直方图+支持向量机(histogram of oriented gradients,support vector machine,HOG+SVM)方法进行零件字符识别,设计了一套基于机器视觉的汽车零件字符检测系统。首先选用Retinex算法增强零件字符图像,结合双边滤波方法对零件字符图像进行滤波去噪,获得质量较好的字符图像,使用HOG+SVM方法进行零件字符识别。Hong等[2]在《Wireless Sensor Network Physical Layer Authentication Technology Based on Dynamic Prediction of Electromagnetic Fingerprints》中设计了一种基于电磁指纹动态预测的无线传感器网络物理层认证机制,使用长短期记忆网络(long short-term memory,LSTM)网络来学习和预测受无线信道影响的电磁指纹的动态,并将合法发射机的独特电磁指纹差异与收发机的信道对应变化相结合,以改善来自合法通信和攻击链路的电磁指纹之间的差异,进一步提高了电磁指纹认证的准确性。对于纹理特征的识别,赵玉兰[3]在《基于纹理结构的指纹匹配算法的研究与应用》中提出利用Poincare指数计算方法对指纹图像的纹理结构特征进行指纹特征提取和匹配算法。施佺[4]提出了一种在灰度化下通过捕捉图像底层特征,利用分布式计算进行图像识别的基于灰度的分布式图像底层特征识别方法。
使用HOG+SVM、Poincare指数、机器学习等方法[5-8]提取汽车零部件纹理特征操作简单,且速度较快,但存在一定的不足[9-12]。对于汽车零部件的材料真伪识别等实际应用场景,由于多种材料的微观图像类型存在多样化特点,其微观特征图像的处理难度较高,采用单一的图像纹理特征提取方法的防伪识别模型的泛化能力较弱,鲁棒性较低,易导致丢失微观图像细节特征,关键属性点提取效果不理想,影响微观图像的识别匹配结果。
为了克服上述模型泛化问题[13-16],提出一种基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术。通过人工智能自动匹配技术基于微观视觉图像处理和神经网络混合算法对汽车零部件进行防伪特征提取和识别。将采集的汽车零部件材料表面微观视觉特征图像进行频域变换、滤波、降噪处理,根据二维频域特征判断当前纹理属于连续型、非连续型、轮廓型的纹理类型,针对不同的纹理从算法库中选择不同的算法,对纹理特征进一步关键属性特征点提取分析[17-22]。选取深度学习框架卷积神经网络(convolutional neural networks,CNN)进行搭建汽车零部件微观视觉特征识别模型,与先验特征库进行匹配分类,实现汽车零部件的真伪识别的目的。
本文中提出的一种基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术,利用人工智能自动匹配技术基于微观视觉图像处理和神经网络混合算法对汽车零部件进行防伪特征提取和识别。通过对汽车零部件的微观视觉特征图像的采集,建立一个包含多种汽车零部件材料表面的微观视觉特征图像数据集。将采集的汽车零部件材料表面微观视觉特征图像进行图像预处理过程,采用图像处理算法对采集到的特征图像进行频域变换、滤波、降噪处理,根据二维频域特征判断当前纹理属于连续型、非连续型、轮廓型的纹理类型,针对不同的纹理从算法库中选择不同的算法,对纹理特征进一步关键属性特征点提取分析。上述的算法库包括Poincare指数算法、灰度共生矩阵算法、Freeman链码及其导数特征提取算法等。对于有连续型条纹的常采用Poincare指数算法,对于非连续型纹理,常采用灰度共生矩阵(gray-level co-occurrence matrix,GLCM)方法对纹理进行特征提取和分析,对于轮廓型纹理,采用Freeman链码及其导数特征提取算法。采用这些算法提取特征以后,选取深度学习框架卷积神经网络CNN框架进行搭建汽车零部件微观视觉特征识别模型,与先验特征库进行匹配分类,最终得到匹配汽车零部件的真伪结果。
本文中对于汽车零部件材料表面的微观特征图像预处理包括:将采集的汽车零部件微观特征图像进行图像分割、求取微观特征图像方向图、微观特征图像增强及滤波、微观特征图像二值化及细化的等操作步骤。
由于汽车零部件微观特征图像的区域有存在背景区的概率,影响了汽车零部件微观特征图像的识别准确率,可以采用图像分割处理将背景区域分割消除,降低由于微观电子显微镜等观测工具造成的外部影响因素产生的观测噪声对于汽车零部件微观特征图像的识别的影响。然后求取其方向图,由于汽车零部件的微观特征图像是一种具有一定纹路走向的多边缘有向图,本文中利用汽车零部件微观特征图像的纹理性和方向性,通过计算方向场作为它的方向图。最后采用二维Gabor滤波器对汽车零部件微观特征图像进行图像增强和滤波处理,去除图像噪声使微观图像的特征纹理有明显的灰度值差异,保留汽车零部件材料表面纹理明显的特征信息。
对汽车零部件微观特征图像进行微观图像分割处理。汽车零部件微观特征图像f(i,j)在小的局部区域是平稳的且可用模型来描述为
$f(i, j)=m_{1 f}(i, j)+\delta_{f}(i, j) w(i, j)$
式(1)中:m1f(i,j)、δf(i,j)分别为(i,j)在(i,j)点的小邻域中的局部均值和方差;w(i,j)为一个0均值单位方差的高斯过程。
对于某像素点(i,j)大小为(2Q+1)(2Q+1)的邻域,有
m 2 f = 1 2 Q + 1 ) 2 k = - Q Q l = - Q Q f ( i + k , j + l ) c 2 f ( i , j ) = δ f 2 = 1 2 Q + 1 ) 2 ×     k = - Q Q l = - Q Q f 2 ( i + k , j + l ) - m 1 f 2 ( i , j ) =       m 2 f ( i , j ) - m 1 f 2 ( i , j )
式(2)中:m2fc2f分别为τ=0时(i,j)点的二阶矩和二阶累积量。
m 3 f ( i , j ) = 1 2 Q + 1 ) 2 k = - Q Q l = - Q Q f 3 ( i + k , j + l ) c 3 f = m 3 f ( i , j ) - 3 m 1 f ( i , j ) m 2 f ( i , j ) + 2 m 1 f 2 ( i , j )
式(3)中:m3fc3f分别为τ1=τ2=0时(i,j)点的三阶矩和三阶累积量。
Q=4时,在汽车零部件微观特征图像的前景区和背景区分别取8×8的块,通过灰度直方图比较,汽车零部件微观特征图像的前景区灰度主要分布在黑(灰度值为0)白(灰度值为255)两端,呈现规律性分布,方差很大。而汽车零部件微观特征图像的背景区灰度主要由噪声组成,可近似满足高斯分布。通过计算三阶累积量,根据实际的图像灰度值参数设置适当的阈值T,当c3f>T时,该块即为微观特征图像的背景区区域,将此部分区域进行割除。
随后求汽车零部件取微观特征图像的方向图,I(i,j)代表汽车零部件微观特征图像在(i,j)处的灰度值。将图像分成大小为M×M的小块,大块大小设为N×N,其中,对于MN的取值,使得其N 2 3M;基于sobel算子计算大块中每个像素I(i,j)在x轴和y轴上的梯度DxDy。即
D x ( i , j ) = [ I ( i - 1 , j - 1 ) + 2 I ( i - 1 , j ) +         I ( i - 1 , j + 1 ) ] - [ I ( i + 1 , j - 1 ) +         2 I ( i + 1 , j ) + I ( i + 1 , j + 1 ) ] D y ( i , j ) = [ I ( i - 1 , j - 1 ) + 2 I ( i , j - 1 ) +         I ( i + 1 , j - 1 ) ] - [ I ( i - 1 , j + 1 ) +         2 I ( i , j + 1 ) + I ( i + 1 , j + 1 ) ]
计算以像素点(i,j)为中心的大块的方向θ(i,j),即
$\begin{array}{c}\theta(i, j)=\frac{1}{2} \tan ^{-1}\left[\frac{\sum_{i=0}^{N-1} \sum_{j=0}^{N-1} 2 D_{x}(i, j) D_{y}(i, j)}{\sum_{i=0}^{N-1} \sum_{j=0}^{N-1}\left(D_{x}^{2}(i, j) D_{y}^{2}(i, j)\right)}\right], \\D_{x} \neq 0 \text { 且 } D_{y} \neq 0\end{array}$
当大块中DxDy为零的数目达到一定程度,如多于大块总像素点数的80%时,θ(i,j)应直接设为0或π。将该N×N大块的方向θ作为M×M小块的方向保存起来,循环计算下一块的方向。
然后对汽车零部件微观特征图像进行微观图像增强及滤波处理。选用具有良好的方向和频率选择性的二维Gabor滤波器,去除图像噪声,保留微观图像的纹理结构。在对汽车零部件微观特征图像进行滤波前,先对其中具有明显材料属性特征的区域进行归一化处理,将它们的均值和方差分别都固定为常数。归一化可以消除传感器噪声和由于压力不同而造成的灰度值差异。这里我们对汽车零部件微观特征图像采用分块处理的方式。定义I(i,j)为像素(i,j)处的灰度值,Aiηi分别为块Si的平均值和方差,ζi(x,y)为像素(x,y)处归一化后的灰度值。对块Si中的所有像素,归一化后的图像定义为
$\zeta_{i}(x, y)=\left\{\begin{array}{ll}A_{0}+\sqrt{\frac{\eta_{0}\left[I(x, y)-A_{i}\right]^{2}}{\eta_{i}}}, & I(x, y)>A_{i} \\A_{0}-\sqrt{\frac{\eta_{0}\left[I(x, y)-A_{i}\right]^{2}}{\eta_{i}}}, & \text { 其他 }\end{array}\right.$
式(6)中:A0η0分别为期望的均值和方差。归一化是对所有的像素统一进行,因此它不会改变汽车零部件微观特征图像的纹理结构。
在汽车零部件微观特征图像中选取16×16大小的子块微观特征图像,二维Gabor函数在空域的数学表达式为
$\begin{aligned}G(x, y)= & \exp \left[-\frac{(x \cos \theta+y \sin \theta)^{2}+\gamma^{2}(-x \sin \theta+y \cos \theta)^{2}}{2 \sigma^{2}}\right] \times \\& \exp \left[\mathrm{i} \frac{2 \pi(x \cos \theta+y \sin \theta)}{\lambda}\right]\end{aligned}$
式(7)中: λ为波长,它的值通常大于等于2,以像素为单位,不能大于输入图像尺寸的五分之一。θ表示方向,取值为0°~360°,指定了Gabor函数并行条纹的方向。γ表示长宽比(空间纵横比),决定了Gabor函数曲线形状的椭圆率, 通常该值为0.5;当γ=1时, 曲线形状是圆的;当γ<1时, 其形状沿着平行条纹方向不断拉伸。σ表示高斯部分的标准差,其值不能直接给定,受到滤波器中心频率的制约。xy表示图像像素点的空间位置坐标。
则汽车零部件微观特征图像的经过图像滤波和增强后的特征图表示为
$H(x, y)=\zeta_{i}(x, y) G(x, y)$
由于汽车零部件的微观特征图像的频域的某一特定分量包含了图像空间的分布情况,基于傅里叶频谱对纹理特征的刻画能力,在二维频域内对汽车零部件微观特征图像的纹理特征进行属于连续型、非连续型的纹理类型的判断和分类。傅里叶谱纹理分析通过傅里叶变换将图像从空间域转换到频域,从而得到汽车零部件微观特征图像的频率分布。通过对频率分布的分析,可以了解汽车零部件微观特征图像中不同频率成分的分布情况,从而揭示汽车零部件微观特征图像的纹理特征,对其进行正确分类。在进行特征纹理分类后,根据不同的纹理类型,将通过自动匹配算法匹配与之相合适的纹理特征提取算法对其进行关键属性点的提取和分析。
将汽车零部件微观特征图像从空间域变换为频域,对于M×N的汽车零部件微观特征图像,如果该微观特征图像的纹理特征属于二维离散数据,则其进行傅里叶变换的过程为
$F(u, v)=\sum_{x=0}^{M-1} \sum_{y=0}^{N-1} f(x, y) \mathrm{e}^{-\mathrm{j} 2 \pi\left(\frac{u x}{M}+\frac{v y}{N}\right)}$
将汽车零部件微观特征图像从空间域变换为频域,如果汽车零部件微观特征图像的纹理特征属于二维连续数据,则其进行傅里叶变换的过程为
F(u,v)= -   -  f(x,y)e-j2π(ux+vy)dxdy
根据上述的微观特征图像分类匹配算法的汽车零部件材料表面的微观特征图像纹理分类结果,针对不同的纹理从算法库中选择不同的算法,对纹理特征进一步关键属性特征点提取分析。上述的算法库包括Poincare指数算法、Freeman链码及其导数特征提取算法、灰度共生矩阵算法等。对于有连续型条纹的采用Poincare指数算法,对于轮廓型纹理,采用Freeman链码及其导数特征提取算法,对于非连续型纹理,采用灰度共生矩阵(GLCM)方法对纹理进行特征提取和分析。提取出具有明显特征信息的特征点作为各个汽车零部件微观特征图像的关键属性点。
对于连续型条纹采用的Poincare指数算法,随机选择一个数据点作为初始中心点,在高维空间中使用非欧几里德空间中的Poincare距离来衡量数据点之间的距离,通过迭代方式逼近数据集的几何中心。不同的汽车零部件微观特征图像的关键属性点,其Poincare指数不同。首先随机初始化数据点在嵌入式空间中的位置,然后通过最小化Poincare距离来调整数据点在嵌入式空间中的位置,以使得数据点在低维空间中更好地表示原始数据之间的关系,最后迭代优化步骤,直到满足停止条件(如达到最大迭代次数或误差收敛)。 由于在微观特征图像纹理方向场计算中采用了分块计算的方法,于是在纹理图像方向场中的关键属性点附近,取相应分块的8邻域区域由汽车零部件微观特征图像预处理的方向场得到θ(α),即α=β1,β2,βi,…,β8(i=1,2,…,8),并对其进行深层方向场归一化优化处理,其Poincare指数的计算公式为
$\begin{aligned}P & =\sum_{i=1}^{8} \Delta(i)=\sum_{i=1}^{8}\left(\gamma \hat{\theta}_{i}+\lambda\right) \\& =\sum_{i=1}^{8}\left\{\gamma\left[\frac{\theta_{i}+\frac{1}{8} \sum_{i=1}^{8} \theta_{i}}{\sqrt{\frac{1}{8} \sum_{i=1}^{8}\left(\theta_{i}+\frac{1}{8} \sum_{i=1}^{8} \theta_{i}\right)^{2}+\varepsilon}}\right]+\lambda\right\}\end{aligned}$
式(11)中:γλ为可学习的参数;ε为趋近于0的值。
$\hat{\theta}_{i}=\left\{\begin{array}{ll}\varphi(i), & |\varphi(i)|<\pi / 2 \\\varphi(i)+\pi, & \varphi(i) \leqslant-\pi / 2 \\\varphi(i)-\pi, & \varphi(i) \geqslant \pi / 2\end{array}\right.$
$\begin{array}{l} \varphi(i)= \theta\left(\alpha^{\prime}\right)-\theta(\alpha) \\= \frac{1}{2}\left[\tan ^{-1}\left\{\frac{\sum_{i=0}^{N-1} \sum_{j=0}^{N-1} 2 D_{a_{x}^{\prime}}(i, j) D_{a_{y}^{\prime}}(i, j)}{\sum_{i=0}^{N-1} \sum_{j=0}^{N-1}\left[D_{a_{x}^{\prime}}^{2}(i, j) D_{a_{y}^{\prime}}^{2}(i, j)\right]}\right\}-\right. \\\left.\tan ^{-1}\left\{\frac{\sum_{i=0}^{N-1} \sum_{j=0}^{N-1} 2 D_{a_{x}}(i, j) D_{a_{y}}(i, j)}{\sum_{i=0}^{N-1} \sum_{j=0}^{N-1}\left[D_{a_{x}}^{2}(i, j) D_{a_{y}}^{2}(i, j)\right]}\right\}\right] \\D_{x} \neq 0 \text { 且 } D_{y} \neq 0 \\\alpha^{\prime}=(\alpha+1) \bmod 8, \alpha=\beta_{1}, \beta_{2}, \cdots, \beta_{i}, \cdots, \beta_{8} \\(i=1,2, \cdots, 8)\end{array}$
式(13)中:DxDy为块中每个像素I(i,j)在x轴和y轴上的基于sobel算子的梯度DxDy
对于非连续型条纹采用的灰度共生矩阵算法采用微观图像中像素灰度级的统计信息,通过计算像素之间的空间关系来描述微观图像纹理特征,区分不同纹理的图像区域。首先定义一个灰度偏移方向,通常为水平、垂直、45°和135°四个方向。然后对于每个像素点,计算与其相邻指定偏移方向上的像素点的灰度值对出现的频率。最后根据计算结果构建一个灰度共生矩阵,即GLCM。矩阵的行和列代表灰度级,矩阵中的每个元素表示对应灰度级对出现的频率。然后计算灰度共生矩阵的相似度研究汽车零部件微观特征图像相似度,选取两幅图像,定义为目标图像F和源图像G,其灰度等级均为M,灰度共生矩阵分别为fg,两者的相似度值为S,以巴氏距离为基础进行计算基相似度D(f,g),再加入灰度共生矩阵的能量及对比度的微观图像特征相似性混合参考因子Δ(f,g),其计算公式为
$\begin{aligned}S & =1-D(\boldsymbol{f}, \boldsymbol{g}) \Delta(\boldsymbol{f}, \boldsymbol{g}) \\& =1-\sqrt{1-\sum_{i=0}^{m-1} \sum_{j=0}^{m-1} \sqrt{f_{i j} g_{i j}}} \frac{\operatorname{cov}[F(e, c), G(e, c)]}{\sigma[F(e, c)] \sigma[G(e, c)]} \\& =1-\sqrt{1-\sum_{i=0}^{m-1} \sum_{j=0}^{m-1} \sqrt{f_{i j} g_{i j}}} \times \\& \frac{\operatorname{cov}\left\{\sum_{i=0}^{m-1} \sum_{j=0}^{m-1} f_{i j}\left[f_{i j}+(i-j)^{2}\right], \sum_{i=0}^{m-1} \sum_{j=0}^{m-1} g_{i j}\left[g_{i j}+(i-j)^{2}\right]\right\}}{\sigma\left\{\sum_{i=0}^{m-1} \sum_{j=0}^{m-1} f_{i j}\left[f_{i j}+(i-j)^{2}\right]\right\} \sigma\left\{\sum_{i=0}^{m-1} \sum_{j=0}^{m-1} g_{i j}\left[g_{i j}+(i-j)^{2}\right]\right\}}\end{aligned}$
式(14)中:S表示目标图像与源图像的纹理相似度,此相似度可以量化两图灰度共生矩阵的相似性,若S=0说明目标与背景的纹理特征完全不同;若S=1说明目标与背景的纹理特征完全一致;S越大,目标与源纹理特征相差越小,说明目标图像与源特征图像的纹理相似性越好;e为灰度共生矩阵的能量,反映了微观特征图像灰度分布均匀程度和纹理粗细度;c为灰度共生矩阵的对比度,反映了图像纹理沟纹的深浅程度。
对于轮廓型纹理采用Freeman链码及其导数特征提取算法,进行微观图像的特征提取处理。将微观图像轮廓上的点序列用一系列数字编码表示,每个数字代表了从当前点到下一个点的移动方向,通常用0~7的数字表示8个可能的移动方向。导数特征提取算法是一种基于Freeman链码的特征提取方法,通过对Freeman链码序列进行处理,可以提取出更具有区分性的特征信息。首先对轮廓进行边界提取,得到轮廓上的点序列,根据轮廓上的点序列生成Freeman链码,将每个点的移动方向编码为0~7的数字,对生成的Freeman链码序列进行导数操作,计算相邻两个数字之间的差值,得到导数序列。然后对导数序列进行进一步处理,如平滑、归一化等,最后使用提取出的导数特征进行微观特征图像的纹理识别和形状匹配等任务。
根据上述关键属性点提取分析模块提取的各个汽车零部件微观特征图像的关键属性点,对比出汽车零部件的真伪零件产品材料表面的特征纹理区别,并作为后续汽车零部件防伪识别特征提取算法模型的判断汽车零部件产品的真伪性的判断重要依据,即后述的汽车零部件微观视觉特征识别模型中的先验特征库。通过深度学习神经网络框架CNN对上述的汽车零部件微观特征图像的关键属性点进行学习训练,搭建汽车零部件微观视觉特征识别模型,与先验特征库进行匹配分类,最终得到防伪识别汽车零部件的真伪结果。
本文组织了大量实验来验证人工智能自动匹配技术基于微观视觉图像处理和神经网络混合算法对汽车零部件进行防伪特征提取和识别的有效性,包括数据对比分析、可视化验证分析等。汽车零部件材料表面微观视觉特征图像数据集、图像预处理、实验设计与参数评价如下所述。
实验选取同一汽车类型的来自不同生产厂的陶瓷刹车片零部件作为实验样本,采集其表面微观视觉特征图像作为汽车零部件材料表面微观视觉特征图像数据集来验证该方法的有效性。数据集包含100张汽车陶瓷刹车片微观视觉特征图像,选择70张作为训练样本、10 张作为验证样本、20张作为测试样本。
计算汽车零部件微观视觉特征图像特征参数作为深度学习CNN神经网络的训练参数,搭建汽车零部件微观视觉特征识别模型。本实验采用了灰度共生矩阵的能量、对比度、相关度、熵等来作为特征参数,来描述汽车零部件微观视觉图像纹理信息。
汽车零部件材料表面微观视觉特征图像处理采用Matlab R2018b中实现,汽车零部件微观视觉特征识别CNN神经网络模型使用64位Ubuntu18.04操作系统,环境配置为Python3.8、PyTorch1.4.0结合Pycharm编译器实现。
将采集的汽车零部件(陶瓷刹车片)材料表面微观特征图像进行图像分割、求取微观特征图像方向图、微观特征图像增强及滤波、微观特征图像二值化及细化的等操作步骤,对图像进行预处理。
图1(a)所示为汽车陶瓷刹车片伪品原图像,图1(b)所示为汽车陶瓷刹车片真品原图像。通过真伪汽车陶瓷刹车片的微观特征图像对比可以看出二者之间的材质差异,后续将对其图像进行预处理,处理结果如图2所示。
图2所示,通过改变图像像素灰度值,提升微观图像对比度、亮度,增强图像细节特征,为后续特征参数和关键属性点的提取提供基础。
图3所示为自动匹配特征提取算法处理前后的汽车陶瓷刹车片真伪产品图像相关性特征参数提取结果。
通过汽车陶瓷刹车片的相关性特征参数对比下的显著提升,为自动匹配特征提取算法对于汽车陶瓷刹车片真伪产品防伪识别效率提供便利,大大提高了模型对真伪汽车陶瓷刹车片的辨别能力。
为了提升汽车零部件防伪特征提取的泛化能力,提出的基于微观视觉和神经网络的汽车零部件防伪特征提取算法自动匹配技术,通过人工智能自动匹配技术基于微观视觉图像处理和神经网络混合算法对汽车零部件进行防伪特征提取和识别。
首先,提出的基于微观视觉和神经网络的防伪特征提取算法,结合了频域变换、滤波、降噪处理以及深度学习技术,显著提高了汽车零部件防伪特征的提取和识别准确性。
其次,通过对二维频域特征的分析,能够有效判断零部件表面纹理的类型(连续型、非连续型、轮廓型),为后续的特征提取和分析提供了精确依据。
然后,针对不同纹理类型,采用不同算法提取关键特征点,并通过深度学习框架(如CNN)对提取的微观视觉特征进行识别,与先验特征库匹配,实现了高效的真伪识别。
本文所提算法能够有效滤除微观图像中的噪声,提高了特征提取的质量,并保证了防伪识别结果的稳定性和可靠性。实验结果表明,该算法在多个测试数据集上均表现出较强的泛化能力,能够适应不同汽车零部件的防伪特征提取和识别需求。通过与先验特征库的匹配分类,该算法在汽车零部件真伪鉴定方面,较传统方法具有更高的判断准确率,提升了防伪识别系统的整体性能。结合微观视觉图像处理与神经网络技术的创新应用,使得防伪识别系统不仅具备较高的准确度,还具有较好的鲁棒性和灵活性,能够适应不同的实际应用场景。
  • 海关总署科研项目(2024KJ07)
  • 海关总署科研项目(2024HK063)
参考文献 引证文献
排序方式:
[1]
袁纵青. 基于机器视觉的汽车零部件字符检测系统设计与实现[D]. 徐州: 中国矿业大学, 2020.
Yuan Zongqing. Design and implementation of character detection system for auto parts based on machine vision[D]. Xuzhou: China University of Mining and Technology, 2020.
[2]
Hang D, Jing J. Wireless sensor network physical layer authentication technology based on dynamic prediction of electromagnetic fingerprints[J]. Academic Journal of Computing Information Science, 2022, 5(11): 18-27.
[3]
赵玉兰. 基于纹理结构的指纹匹配算法的研究与应用[J]. 电脑知识与技术, 2010, 6(22): 6309-6310.
Zhao Yulan. Research and application of fingerprint matching algorithm based on texture structure[J]. Computer Konwledge and Technology, 2010, 6(22): 6309-6310.
[4]
施佺. 基于灰度的分布式图像底层特征识别方法及系统: CN201510671757.8[P]. 2016-02-24.
Shi Quan. Method and system of distributed image bottom feature recognition based on gray scale: CN201510671757.8[P]. 2016-02-24.
[5]
徐佳楠, 张天瑞, 李玉龙. 基于自适应遗传-粒子群优化算法的风电场微观选址优化[J]. 科学技术与工程, 2023, 23(16): 6917-6922.
Xu Jiannan, Zhang Tianrui, Li Yulong. Micro-location and optimization of wind farm based on the adaptive GA-PSO algorithm[J]. Science Technology and Engineering, 2023, 23(16): 6917-6922.
[6]
王莉, 任健荣, 王涛, 等. 基于区块链的粮食防伪溯源系统的设计与实现[J]. 科学技术与工程, 2023, 23(4): 1625-1634.
Wang Li, Ren Jianrong, Wang Tao, et al. Design and implementation of food security traceability system based on blockchain[J]. Science Technology and Engineering, 2023, 23(4): 1625-1634.
[7]
洪坤明, 刘新亮, 高圣乔. 基于联盟区块链的水产养殖品质量追溯系统的设计与实现[J]. 科学技术与工程, 2019, 19 (35): 79-86.
Hong Kunming, Liu Xinliang, Gao Shengqiao. Design and implementation of traceability system for aquaculture products based on coalition block chain[J]. Science Technology and Engineering, 2019, 19(35): 79-86.
[8]
Li T, Chen H, Yuan J, et al. Quality risk propagation of complex product collaborative manutacturing supply chain network based on CN and SoV[J]. Discrete Dynamics in Nature and Soeiety, 2020(4): 1-16.
[9]
Wang N, Yu Q, Wan H, et a1. Adaptive scheduling for multi-cluster time—triggered train communication networks[J]. IEEE Transactions on Industrial Informatics, 2018, 15(2): 1120-1130.
[10]
Fan L, Yan X, Li H, et al. Bidirectional image denoising with blurred image feature[J]. Pattern Recognition, 2024, 153: 110563.
[11]
Das D, Naskar R. Image splicing detection using low-dimensional feature vector of texture features and Haralick features based on gray level co-occurrence matrix[J]. Signal Processing: Image Communication, 2024, 125: 117134.
[12]
Shubhra P, Bhojan R. Gray level co-occurrence matrix based fully convolutional neural network model for pneumonia detection[J]. International Journal of Electrical and Computer Engineering Systems, 2024, 15(4): 369-376.
[13]
韩虎, 吕宪勇, 李云霞, 等. 基于可视化分析模型的汽车电控系统需求开发方法[J]. 科学技术与工程, 2024, 24(7): 2956-2965.
Han Hu, Xianyong, Li Yunxia, et al. Requirements development method of automotive electronic control system based on visual analysis model[J]. Science Technology and Engineering, 2024, 24(7): 2956-2965.
[14]
唐嘉男, 孟祥瑞. 基于多尺度信息提取和特征融合的皮肤镜图像分割算法[J]. 湖北民族大学学报(自然科学版), 2024, 42(2): 226-232.
Tang Jianan, Meng Xiangrui. Dermoscopic image segmentation algorithm based on multi-scale information extraction and feature fusion[J]. Journal of Hubei Minzu University (Nature Science Edition), 2024, 42(2): 226-232.
[15]
李云飞, 刘菊琨, 柳青. 改进RSA算法的安全性分析[J]. 计算机应用与软件, 2018, 35(6): 309-312.
Li Yunfei, Liu Jukun, Liu Qing. Improved RSA algorithm security analysis[J]. Computer Applications and Software, 2018, 35(6): 309-312.
[16]
赵维. 基于区块链技术的农业食品安全追溯体系研究[J]. 技术经济与管理研究, 2019(1): 16-20.
Zhao Wei. Research on traceability system of agricultural-food safety based on block chain technology[J]. Journal of Technical Economics & Management, 2019(1): 16-20.
[17]
孟超, 周倩, 郭林, 等. 基于相关件传输模型的无线链路质量估计方法及路由优化算法[J]. 电子学报, 2022, 50(10): 2409-2424.
Meng Chao, Zhou Qian, Guo Lin, et al. Estimation method of wireless link quality and routing optimization algorithm based on correlation transnlission model[J]. Acta Electronica Siniea, 2022, 50(10): 2409-2424.
[18]
Fei M, Shen Z, Song Z, et al. Distillation of multi-class cervical lesion cell detection via synthesis-aided pre-training and patch-level feature alignment[J]. Neural Networks, 2024, 178: 106405.
[19]
Xu J. Image data visualization and communication system based on sensor network simulation and visual feature extraction[J]. Measurement: Sensors, 2024, 33: 101223.
[20]
Zhang H, Wan J, He Z, et al. Sparse agent transformer for unified voxel and image feature extraction and fusion[J]. Information Fusion, 2024, 110: 102455.
[21]
Aysun S, Basri H S, Songul A. Retraction note: hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images[J]. Neural Computing and Applications, 2024, 36 (18): 11033.
[22]
Ahmed J B, Jiang G, Ziaur R, et al. Feature extraction of multimodal medical image fusion using novel deep learning and contrast enhancement method[J]. Applied Intelligence, 2024, 54(7): 5907-5930.
2025年第25卷第19期
PDF下载
121
42
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405631
  • 接收时间:2024-07-26
  • 首发时间:2025-12-22
  • 出版时间:2025-07-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-26
  • 修回日期:2024-12-23
基金
海关总署科研项目(2024KJ07)
海关总署科研项目(2024HK063)
作者信息
    1 南京海关工业产品检测中心, 南京 210005
    2 南京邮电大学通信与信息工程学院, 南京 210003
    3 南京工程学院机械工程学院, 南京 211167
    4 南昌海关技术中心, 南昌 330038

通讯作者:

*方静(1987—),女,汉族,江苏无锡人,硕士,工程师。研究方向:汽车零部件多特征识别等。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405631
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏