Comparative evaluation of threshold-based and CNN-based segmentation methods for multi-modal digital images of geotechnical materials

Comparative evaluation of threshold-based and CNN-based segmentation methods for multi-modal digital images of geotechnical materials

PDF

Zhijie Jian^a^,^b, Jiangfeng Liu^a^,^b^,^*, Shijia Ma^a^,^b^,^*, Zhipeng Wang^a^,^b, Qing Jian^a, Ruinian Sun^a^,^b, Chenghao Wu^a^,^b

Intelligent Geoengineering | 2026, 3(1) : 11 - 35

Less

Intelligent Geoengineering | 2026, 3(1): 11-35

• Full length article •

Comparative evaluation of threshold-based and CNN-based segmentation methods for multi-modal digital images of geotechnical materials

Full

Zhijie Jian^a^,^b, Jiangfeng Liu^a^,^b^,^*, Shijia Ma^a^,^b^,^*, Zhipeng Wang^a^,^b, Qing Jian^a, Ruinian Sun^a^,^b, Chenghao Wu^a^,^b

Affiliations

^aState Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering, China University of Mining and Technology, Xuzhou 221116, China

^bResearch Center for Deep Underground Energy and Subsurface Storage, China University of Mining and Technology, Xuzhou 221116, China

Published: 2026-03-10 doi: 10.1016/j.ige.2026.03.001

Outline

Abstract

Less

This study systematically evaluates the performance of 15 conventional global single-threshold segmentation algorithms and three representative convolutional neural network (CNN) models across multi-modal geotechnical material images, including computed tomography (CT) and scanning electron microscopy (SEM) data. Based on their characteristics, thresholding methods are classified into three categories: histogram-based, entropy-based, and other approaches. Four types of geotechnical material CT images and two types of SEM images were selected as the evaluation datasets, and an objective assessment criterion that does not require manual annotation was proposed. The results indicate that the performance of different thresholding algorithms varies considerably across imaging modalities: the Otsu method performs best on coal and sandstone CT images, the Liu-S method (implemented in the JHNY-DPM software) excels on sandy soil CT images, and the Yen method demonstrates strong robustness on SEM images. However, all thresholding methods fail to effectively segment granite images with uneven grayscale distributions. In contrast, deep learning models exhibit superior performance across all modalities, with U-Net achieving the highest accuracy and stability during both training and validation without noticeable overfitting, significantly outperforming Fcn and Deeplabv3. Further experiments on a combined CT-SEM dataset reveal that despite domain adaptation challenges, U-Net can consistently segment complex geotechnical structures across different imaging modalities. Overall, the analysis demonstrates that deep learning models substantially enhance the accuracy and robustness of multi-modal geotechnical image segmentation, providing guidance for algorithm selection and supporting the unified processing of multi-source imaging data toward automation and intelligent analysis in digital geotechnical research.

Key words

Multi-modal image segmentation / Thresholding algorithms / Geotechnical materials / Digital rock images / Deep learning / JHNY-DPM

Cite this Article

Zhijie Jian, Jiangfeng Liu, Shijia Ma, Zhipeng Wang, Qing Jian, Ruinian Sun, Chenghao Wu. Comparative evaluation of threshold-based and CNN-based segmentation methods for multi-modal digital images of geotechnical materials[J]. Intelligent Geoengineering, 2026 , 3 (1) : 11 -35 . DOI: 10.1016/j.ige.2026.03.001

Full Text

Less

Funding

Less

National Key Research and Development Program of China(2025YFE0116200)
National Natural Science Foundation of China(52474155; W2521168)
Natural Science Foundation of Jiangsu Province(BK20240107)
Scientific Research Innovation Capability Support Project for Young Faculty(SRICSPYF-ZY2025043)

Appendix

Less

Year 2026 volume 3 Issue 1

PDF

Cite this Article

BibTeX

Article Info

doi: 10.1016/j.ige.2026.03.001

Receive Date：2026-01-04
Online Date：2026-06-18
Published：2026-03-10

Article Data

Affiliations

History

Received：2026-01-04
Revised：2026-03-01
Accepted：2026-03-22

Funding

National Key Research and Development Program of China(2025YFE0116200)

National Natural Science Foundation of China(52474155; W2521168)

Natural Science Foundation of Jiangsu Province(BK20240107)

Scientific Research Innovation Capability Support Project for Young Faculty(SRICSPYF-ZY2025043)

Affiliations

^aState Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering, China University of Mining and Technology, Xuzhou 221116, China

^bResearch Center for Deep Underground Energy and Subsurface Storage, China University of Mining and Technology, Xuzhou 221116, China

Corresponding:

^* China University of Mining and Technology, Xuzhou 22116, China. E-mail addresses: jeafliu@cumt.edu.cn (J. Liu)

E-mail addresses: shijiama@cumt.edu.cn (S. Ma).

References

Share

https://castjournals.cast.org.cn/joweb/igeo/EN/10.1016/j.ige.2026.03.001

Share to

Scan QR to access full text

Cite this article

BibTeX

Citations

表12种不同金属材料的力学参数

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

BibTeX
EndNote
RefWorks
TxT

Articles: Latest Articles; Most Read; Collections

Updates: Events; News; Multimedia

About: About Us

Contact

No. 86 Xueyuan South Road, Haidian District, Beijing

100081

010-62199257

qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House