An image recognition and multi-parameter quantitative characterization system for fractures in roadway rocks

Authors

• XIONG Yu, School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510640, ChinaFollow
• JIANG Lichun, School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510640, China
• KONG Dezhong, Mining College, Guizhou University, Guiyang 550025, ChinaFollow
• LI Jinzhu, Institute of Safety Science & Engineering, South China University of Technology, Guangzhou 510640, China

Abstract

Objective Conventional measurement methods for rock fractures suffer from low efficiency and high subjectivity. On the other hand, simple image recognition techniques struggle to achieve high-precision multi-parameter integrated analysis of rock fractures in complex roadway environments. To address these challenges, this study aims to develop an image recognition and multi-parameter quantitative characterization system for rock fractures. Methods At the core of the system is the formulation of a combined image preprocessing strategy. Specifically, fracture segmentation is conducted based on adaptive threshold binarization, isolated noise points are removed using morphological opening, and median filtering is introduced to perform the refined polishing of fracture boundaries. These processes help enhance the boundary clarity and structural integrity of the binary images. Morphological thinning is further combined, and core processing modules, including interconnected component analysis, regional attribute acquisition, and effective fracture selection, are integrated into the system. Then, based on scale calibration, the proposed system achieves the simultaneous calculation and accurate extraction of multi-dimensional fracture parameters, including length, width, area, density, and dip angle. Results and Conclusions The proposed system preserved complete fracture details under challenging conditions such as low illumination and moist rock masses, yielding fewer false negatives and false positives compared to the conventional Canny operator and few-shot learning models. For single fractures, the processing approaches based on denoised and skeleton images achieved comparable accuracy in the extraction of key fracture parameters. Using the combination of the two approaches, the relative errors of fracture lengths and angles were controlled within 7% and 2%, respectively. For complex fracture networks, the recognition results of the proposed system aligned highly with manual measurements. Specifically, the proportion of fractures with lengths exceeding 10 cm in the surveyed area was determined at approximately 21% and 24% by the proposed system and manual measurements, respectively, and consistent dominant dip angles of the fractures were revealed. The proposed system enables the rapid and automatic generation of visualized results, such as histograms illustrating the dip angle and size distributions of fractures. These visualized results can distinctly reveal the developmental patterns of fractures, thereby providing critical support for assessing the stability of roadway rocks. Additionally, the proposed system has the potential to expand from two-dimensional parameter extraction to three-dimensional spatial analysis and to connect rapid field diagnosis to engineering simulation, holding broad prospects for engineering application and secondary development.

Keywords

roadway surrounding rock, rock fracture, image recognition, morphological processing, fracture characterization, quantitative statistics

DOI

10.12363/issn.1001-1986.25.12.0953

Recommended Citation

XIONG Yu, JIANG Lichun, KONG Dezhong, et al. (2026) "An image recognition and multi-parameter quantitative characterization system for fractures in roadway rocks," Coal Geology & Exploration: Vol. 54: Iss. 8, Article 19.
DOI: 10.12363/issn.1001-1986.25.12.0953
Available at: https://cge.researchcommons.org/journal/vol54/iss8/19

Reference

[1] 陈军，张波，庄兴岳，等. 基于探地雷达的岩体裂隙动态扩展过程识别方法[J/OL]. 工程科学与技术，2025：1–16 [2025-06-17]. https://doi.org/10. 12454/j.jsuese.202500323. CHEN Jun，ZHANG Bo，ZHUANG Xingyue，et al. Identification method of dynamic propagation process of rock fracture based on ground penetrating radar[J/OL]. Advanced Engineering Sciences，2025：1–16 [2025-06-17]. https://doi.org/10. 12454/j.jsuese.202500323.

[2] 孙月龙,崔洪庆,关金锋. 基于图像识别的煤层井下宏观裂隙观测[J]. 煤田地质与勘探,2017,45(5):19−22 SUN Yuelong,CUI Hongqing,GUAN Jinfeng. Image recognition–based observation of macro fracture in coal seam in underground mine[J]. Coal Geology & Exploration,2017,45(5):19−22

[3] XIONG Yu,JIANG Lichun,KONG Dezhong,et al. Driving mechanism of stress path to fissure propagation in surrounding rock during parallel roadway excavation[J]. Engineering Fracture Mechanics,2025,330:111681.

[4] 王军祥,曾相森,徐晨晖,等. 基于图像处理技术的岩体裂隙定量识别方法研究[J]. 地下空间与工程学报,2022,18(2):446−457 WANG Junxiang,ZENG Xiangsen,XU Chenhui,et al. Study on quantitative identification method of rock fracture based on image processing technology[J]. Chinese Journal of Underground Space and Engineering,2022,18(2):446−457

[5] 郑江韬,齐子豪,刘佳存,等. 基于卷积神经网络的煤岩微裂隙提取方法[J]. 矿业科学学报,2022,7(6):680−688 ZHENG Jiangtao,QI Zihao,LIU Jiacun,et al. Segmentation of micro-cracks in fractured coal based on convolutional neural network[J]. Journal of Mining Science and Technology,2022,7(6):680−688

[6] 冯雪健,沈永星,周动,等. 基于CT数字岩心深度学习的煤裂隙分布识别研究[J]. 煤炭科学技术,2023,51(8):97−104 FENG Xuejian,SHEN Yongxing,ZHOU Dong,et al. Multi–scale distribution of coal fractures based on CT digital core deep learning[J]. Coal Science and Technology,2023,51(8):97−104

[7] 王润辉. 数字图像处理[M]. 北京：清华大学出版社，2013.

[8] 马丽莎. 基于数字图像处理的路面裂缝识别方法研究[D]. 南京：东南大学，2018. MA Lisha. Research on pavement crack recognition method based on digital image processing[D]. Nanjing：Southeast University，2018.

[9] 周迎. 数字岩心图像孔裂隙识别及参数提取方法研究[D]. 荆州：长江大学，2024. ZHOU Ying. Research on pore and fracture identification and parameter extraction in digital core image[D]. Jingzhou：Yangtze University，2024.

[10] 赵杰,汪洪法,周明. 融合眼视觉和改进多尺度Retinex的矿岩裂隙图像增强[J]. 金属矿山,2024(12):252−257 ZHAO Jie,WANG Hongfa,ZHOU Ming. Enchantment of ore–rock fissure images based on human visual perception and improved multi–scale Retinex algorithm[J]. Metal Mine,2024(12):252−257

[11] 邓兆鹏,曹茂永,LAXMISHA Rai. 基于改进的区域生长和Hough变换的钻孔图像水平裂隙识别[J]. 科学技术与工程,2019,19(31):239−245 DENG Zhaopeng,CAO Maoyong,LAXMISHA Rai. Horizontal fracture recognition of borehole image based on improved region growing and Hough transform[J]. Science Technology and Engineering,2019,19(31):239−245

[12] 肖福坤,刘欢欢,单磊. 基于连通性阈值分割的煤岩裂隙识别方法[J]. 工矿自动化,2024,50(8):127−134 XIAO Fukun,LIU Huanhuan,SHAN Lei. Coal rock crack recognition method based on connectivity threshold segmentation[J]. Journal of Mine Automation,2024,50(8):127−134

[13] 杨苏. 基于数字照相量测的岩体裂隙识别与表征初步研究[D]. 徐州：中国矿业大学，2017. YANG Su. Preliminary study on identification and characterization of rock fracture based on digital photogrammetry[D]. Xuzhou：China University of Mining and Technology，2017.

[14] 米向东,沈一凡,陈佳耀,等. 基于机器视觉的岩石隧道工作面破碎及滑移特性研究[J]. 土木工程学报,2024,57(增刊2):148−153 MI Xiangdong,SHEN Yifan,CHEN Jiayao,et al. Study on fragmentation and slip characteristics of rock tunnel faces via machine vision[J]. China Civil Engineering Journal,2024,57(Sup.2):148−153

[15] 于佳慧,张博霄,何润辛,等. 基于线结构光的裂隙提取算法研究[J]. 光学技术,2023,49(6):711−716 YU Jiahui,ZHANG Boxiao,HE Runxin,et al. Research on fracture extraction algorithm based on line structured light[J]. Optical Technique,2023,49(6):711−716

[16] 许守春,许向阳,冯宇恒. 基于图像处理的裂缝量化分析[J]. 化工自动化及仪表,2024,51(2):173−180 XU Shouchun,XU Xiangyang,FENG Yuheng. Quantitative analysis of cracks based on image processing[J]. Control and Instruments in Chemical Industry,2024,51(2):173−180

[17] 袁钰鑫. 煤巷掘进工作面围岩裂隙智能识别与三维重构方法研究[D]. 徐州：中国矿业大学，2023. YUAN Yuxin. Research on intelligent identification and 3D reconstruction method of surrounding rock fissures in mining roadway working face[D]. Xuzhou：China University of Mining and Technology，2023.

[18] CHEN Jiayao,ZHOU Mingliang,HUANG Hongwei,et al. Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning[J]. International Journal of Rock Mechanics and Mining Sciences,2021,142:104745.

[19] ZHAO Shuai,ZHANG Dongming,XUE Yadong,et al. A deep learning–based approach for refined crack evaluation from shield tunnel lining images[J]. Automation in Construction,2021,132:103934.

[20] 张东林. 基于深度学习的水下混凝土结构表观裂缝智能识别方法[D]. 广州：广州大学，2025. ZHANG Donglin. Deep learning–based intelligent recognition method for apparent cracks in underwater concrete structures[D]. Guangzhou：Guangzhou University，2025.

[21] ANILKUMAR P,VENUGOPAL P,KUMAR S S,et al. Adaptive multilevel attention deeplabv3+ with heuristic based frame work for semantic segmentation of aerial images using improved golden jackal optimization algorithm[J]. Results in Engineering,2024,24:103164.

[22] 董征,张旭辉,杨文娟,等. 基于DC–UNet的煤矿掘进巷道断面裂隙图像检测方法[J]. 煤田地质与勘探,2024,52(12):224−232 DONG Zheng,ZHANG Xuhui,YANG Wenjuan,et al. A DC–UNet–based image processing method for detecting fractures along roadway sections of coal mines[J]. Coal Geology & Exploration,2024,52(12):224−232

[23] AGARWAL M,GUPTA S K,BISWAS K K. Development of a compressed FCN architecture for semantic segmentation using Particle Swarm Optimization[J]. Neural Computing and Applications,2023,35(16):11833−11846.

[24] 刘阳晓,朱万成,刘文胜,等. 基于倾斜摄影测量的露天矿数值模型重构与计算实例[J]. 采矿与岩层控制工程学报,2021,3(4):043513 LIU Yangxiao,ZHU Wancheng,LIU Wensheng,et al. Refined numerical simulation modeling of open–pit mine based on UAV photogrammetry and case analysis[J]. Journal of Mining and Strata Control Engineering,2021,3(4):043513

[25] 刘丹洋. 基于机器视觉的露天矿边坡裂隙检测及量化统计研究[D]. 西安：西安建筑科技大学，2021. LIU Danyang. Research on detection and quantitative statistics of open–pit slope fractures based on machine vision[D]. Xi’an：Xi’an University of Architecture and Technology，2021.

[26] 李勇,邱一迪,高玮,等. 膨胀土边坡渗透变形的表面裂隙图像特征分析[J]. 工程地质学报,2023,31(1):267−276 LI Yong,QIU Yidi,GAO Wei,et al. Image characteristics analysis of surface cracks in seepage deformation of expansive soil slope[J]. Journal of Engineering Geology,2023,31(1):267−276

[27] 覃红亮,赵翠,朱昱桦,等. 贵州长兴组典型危岩体稳定性关键问题研究[J]. 现代地质,2025,39(4):908−919 QIN Hongliang,ZHAO Cui,ZHU Yuhua,et al. Research on key issues of stability of typical dangerous rock masses in the Changxing Formation, Guizhou Province[J]. Geoscience,2025,39(4):908−919

[28] ZHAO Jun,ZHAO Jianglong,FENG Xiating,et al. An integrated intelligent long-term device for the borehole monitoring of deformation and evolution of fractures in rock masses[J]. Deep Resources Engineering,2026,3:100204.

[29] XU Jinjian,ZHANG Hao,TANG Chaosheng,et al. Automatic soil crack recognition under uneven illumination condition with the application of artificial intelligence[J]. Engineering Geology,2022,296:106495.

[30] DONG Ao,TANG Chaosheng,ZHU Cheng,et al. 3D reconstruction and characterization of soil desiccation cracks using smartphone photogrammetry method[J]. Computers and Geotechnics,2025,186:107384.

[31] 李润青. 基于数字图像处理的路面裂缝提取方法研究[D]. 西安：长安大学，2020. LI Runqing. Pavement crack extraction based on digital image processing[D]. Xi’an：Chang’an University，2020.

[32] 谢明志，樊丁萌，蒋志鹏，等. 基于计算机视觉的混凝土结构裂缝检测研究现状与展望[J/OL]. 西南交通大学学报，2024：1–20 [2024-09-14]. https://link.cnki.net/urlid/51.1277.u.20240913.1853.002. XIE Mingzhi，FAN Dingmeng，JIANG Zhipeng，et al. Research status and prospects of computer vision–based concrete structure crack detection[J/OL]. Journal of Southwest Jiaotong University，2024：1–20 [2024-09-14]. https://link.cnki.net/urlid/51.1277.u.20240913.1853.002.

[33] WANG Shaowei,XU Jiangbo,WU Xiong,et al. Concrete crack recognition and geometric parameter evaluation based on deep learning[J]. Advances in Engineering Software,2025,199:103800.

[34] 陈承浩. 节理裂隙快速辨识与岩体质量三维表征研究[D]. 合肥：合肥工业大学，2021. CHEN Chenghao. Rapid identification of joints and fractures and 3D characterization of rock mass quality[D]. Hefei：Hefei University of Technology，2021.

[35] 田子建,吴佳奇,张文琪,等. 基于Transformer和自适应特征融合的矿井低照度图像亮度提升和细节增强方法[J]. 煤炭科学技术,2024,52(1):297−310 TIAN Zijian,WU Jiaqi,ZHANG Wenqi,et al. An illuminance improvement and details enhancement method on coal mine low–light images based on Transformer and adaptive feature fusion[J]. Coal Science and Technology,2024,52(1):297−310

[36] 伍法权,夏毓,何林恺. 基于采样窗的岩体裂隙图像信息检测方法研究[J]. 工程地质学报,2024,32(6):2064−2071 WU Faquan,XIA Yu,HE Linkai. Research on rock fracture image information detection method based on sampling window[J]. Journal of Engineering Geology,2024,32(6):2064−2071

[37] 吴金,吴顺川,孙贝贝. 岩体暴露面图像中裂隙全自动提取方法研究[J]. 岩土力学,2024,45(9):2621−2632 WU Jin,WU Shunchuan,SUN Beibei. Research on fully automatic extraction of fractures from images of rock mass exposures[J]. Rock and Soil Mechanics,2024,45(9):2621−2632

[38] 吴顺川,孙贝贝,余一松,等. 考虑几何特征的岩体裂隙迹线多尺度图像识别方法[J]. 华中科技大学学报(自然科学版),2024,52(9):101−109 WU Shunchuan,SUN Beibei,YU Yisong,et al. Multi–scale image recognition method of rock mass fracture traces considering geometric features[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition),2024,52(9):101−109

[39] LIU Yangxiao,ZHU Wancheng,LIU Xige,et al. Core fracture identification and dip angle calculation using a deep learning model[J]. Rock Mechanics and Rock Engineering,2025,58(1):1327−1345.

[40] 张丽娜. 彩色图像灰度化方法研究[D]. 兰州：兰州大学，2024. ZHANG Lina. Research on color–to–gray conversion[D]. Lanzhou：Lanzhou University，2024.

[41] GAO Jiazheng,HE Yongsheng,CHEN Yeqing,et al. Optimized binarization algorithm–based method for the image recognition and characterization of explosion damage in rock masses[J]. Engineering Geology,2024,343:107787.

[42] GAO Qiangqiang,MA Liqiang,LIU Wei,et al. Research on the denoising method of infrared thermogram during rock fracture[J]. Infrared Physics & Technology,2023,131:104651.

[43] ESMAEILI M,BENI T,GIGLI G,et al. Rock mass exposure fracture detection through 2D close–range images using image processing techniques:A review[J]. Earth Science Informatics,2025,18(3):494.

[44] 梁艳杰. 基于线状特性及几何分析的复杂节理裂隙检测与评估[D]. 福州：福州大学，2016. LIANG Yanjie. Complicated fracture detection and evaluation based on curvilinear feature and geometry analysis[D]. Fuzhou：Fuzhou University，2016.