Significant developments have been made in crack segmentation tasks within the single-context of modern architectural structures. However, when confronted with the challenges posed by more complex backgrounds and poor lighting conditions, the precision of crack segmentation technologies remains in a continual state of exploration and refinement. Consequently, this paper puts forward a component tree-driven MSSR-RG algorithm originally, primarily based on modified single-scale Retinex (MSSR) and region growing algorithms (CT-MSSR-RG). Initially, the source code of the SSR algorithm was modified to preserve the logarithmic-domain distribution of image data, thereby compensating for insufficient illumination. Subsequently, the vertical hierarchical relationships within the component tree (CT) are constructed by iteratively adjusting the ksize parameter of the MSSR algorithm. Simultaneously, the horizontal component relationships are established through MSSR, threshold segmentation (TS) and RG algorithms. Finally, a masking algorithm is introduced, reformulating the similarity criterion of the RG algorithm (the computations for determining whether pixels belong to the crack)—from function-based calculations to image processing approaches—to accelerate the growth of the CT. Deployed for crack segmentation in Tibetan traditional mural monitoring, a representative scenario for heritage preservation monitoring challenges, the method achieves over 90% F1-score by systematically comparing the segmentation results purely derived from intrinsic image features with high-precision manual pixel-level annotations, confirming its efficiency of crack segmentation under strong interference conditions.
BiratuESSchwenkerFDebeleeTG, et al. (2021) Enhanced region growing for brain tumor MR image segmentation. Journal of Imaging7(2): 22. https://doi.org/10.3390/jimaging7020022
2.
CaoWLiJ (2025) A novel image multitasking enhancement model for underwater crack detection. Structural Health Monitoring24(4): 1969–1990. https://doi.org/10.1177/14759217241228780
3.
Cubero-FernandezARodriguez-LozanoFJVillatoroR, et al. (2017) Efficient pavement crack detection and classification. Eurasip Journal on Image & Video Processing2017(1): 39. https://doi.org/10.1186/s13640-017-0187-0
4.
CuiXWangQDaiJ, et al. (2021) Intelligent crack detection based on attention mechanism in convolution neural network. Advances in Structural Engineering24(9): 1859–1868. https://doi.org/10.1177/1369433220986638
5.
DungCVAnhLD (2019) Autonomous concrete crack detection using deep fully convolutional neural network. Automation in Construction99: 52–58. https://doi.org/10.1016/j.autcon.2018.11.028
6.
EhtishamRQayyumWCampCV, et al. (2024) Computing the characteristics of defects in wooden structures using image processing and CNN. Automation in Construction158: 105211. https://doi.org/10.1016/j.autcon.2023.105211
7.
FengQGaoBLuP, et al. (2018) Automatic seeded region growing for thermography debonding detection of CFRP. NDT & E International99: 36–49. https://doi.org/10.1016/j.ndteint.2018.06.001
8.
GuoFCuiQZhangH, et al. (2024) A new deep learning-based approach for concrete crack identification and damage assessment. Advances in Structural Engineering27(13): 2303–2318. https://doi.org/10.1177/13694332241266535
9.
HoangNDNguyenQL (2018) Metaheuristic optimized edge detection for recognition of concrete wall cracks: a comparative study on the performances of Roberts, Prewitt, Canny, and Sobel algorithms. Advances in Civil Engineering2018(1): 7163580. https://doi.org/10.1155/2018/7163580
10.
HsiehYATsaiYJ (2020) Machine learning for crack detection: review and model performance comparison. Journal of Computing in Civil Engineering34(5): 04020038. https://doi.org/10.1061/(asce)cp.1943-5487.0000918
11.
KheradmandiNMehranfarV (2022) ‘A critical review and comparative study on image segmentation-based techniques for pavement crack detection’. Construction and Building Materials321: 126162. https://doi.org/10.1016/j.conbuildmat.2021.126162
12.
KongSYFanJSLiuYF, et al. (2025) Automated crack assessment and quantitative growth monitoring. Computer-Aided Civil and Infrastructure Engineering36(5): 656–674. https://doi.org/10.1111/mice.12626
13.
LandEH (1986) An alternative technique for the computation of the designator in the Retinex theory of color vision. Proceedings of the National Academy of Sciences83(10): 3078–3080. https://doi.org/10.1073/pnas.83.10.3078
14.
LiQZouQZhangD, et al. (2011) FoSA: F* seed-growing approach for crack-line detection from pavement images. Image and Vision Computing29(12): 861–872. https://doi.org/10.1016/j.imavis.2011.10.003
15.
LiLLiZHanH, et al. (2023) Wooden spoon crack detection by prior knowledge-enriched deep convolutional network. Engineering Applications of Artificial Intelligence126: 106810. https://doi.org/10.1016/j.engappai.2023.106810
16.
LiFMouYZhangZ, et al. (2024) A novel model for the pavement distress segmentation based on multi-level attention DeepLabV3+. Engineering Applications of Artificial Intelligence137: 109175. https://doi.org/10.1016/j.engappai.2024.109175
17.
LiangJWanXLiuQ, et al. (2016) Research on filter selection method for broadband spectral imaging system based on ancient murals. Color Research & Application41(6): 585–595. https://doi.org/10.1002/col.22004
18.
LiuYChoSJrBFS, et al. (2014) Automated assessment of cracks on concrete surfaces using adaptive digital image processing. Smart Structures and Systems14(4): 719–741.
19.
LiuYFLiuJHWeiXC, et al. (2024) An image-based bridge displacement field measurement method with self-vibration elimination. Advances in Structural Engineering28(3): 424–443. https://doi.org/10.1177/13694332241286535
20.
LuWCuiYTengJ (2016) Structural displacement and strain monitoring based on the edge detection operator. Advances in Structural Engineering20(2): 191–201. https://doi.org/10.1177/1369433216660220
21.
LuWQianMXiaY, et al. (2024) Crack_PSTU: crack detection based on the U-Net framework combined with Swin transformer. Structures62: 106241. https://doi.org/10.1016/j.istruc.2024.106241
22.
SunXWangBLiuK (2020) DEM and valley segmentation in remote sensing image based on region growing algorithm. Journal of Physics: Conference Series1693(1): 012174.
TalabAMAHuangZXiF, et al. (2016) Detection crack in image using Otsu method and multiple filtering in image processing techniques. Optik - International Journal for Light and Electron Optics127(3): 1030–1033. https://doi.org/10.1016/j.ijleo.2015.09.147
25.
WangZXuGDingY, et al. (2020) A vision-based active learning convolutional neural network model for concrete surface crack detection. Advances in Structural Engineering23(13): 2952–2964. https://doi.org/10.1177/1369433220924792
26.
WangXWangTLiJ (2023) Advanced crack detection and quantification strategy based on CLAHE enhanced DeepLabv3+. Engineering Applications of Artificial Intelligence126: 106880. https://doi.org/10.1016/j.engappai.2023.106880
YangGWuJHuQ (2018) Rapid detection of building cracks based on image processing technology with double square artificial marks. Advances in Structural Engineering22(5): 1186–1193. https://doi.org/10.1177/1369433218810183
29.
YangJXuYYueH, et al. (2021) Low-light image enhancement based on Retinex decomposition and adaptive gamma correction. IET Image Processing15(5): 1189–1202. https://doi.org/10.1049/ipr2.12097
30.
YinGGaoJGaoJ, et al. (2023) Crack identification method of highway tunnel based on image processing. Journal of Traffic and Transportation Engineering10(3): 469–484. https://doi.org/10.1016/j.jtte.2022.06.006
31.
YuanXWuDWangY, et al. (2025) Semantic segmentation 3333333model based on edge information for rock structural surface traces detection. Engineering Applications of Artificial Intelligence140: 109706. https://doi.org/10.1016/j.engappai.2024.109706
32.
ZakeriHNejadFMFahimifarA (2017) Image based techniques for crack detection, classification and quantification in asphalt pavement: a review. Archives of Computational Methods in Engineering24(4): 935–977. https://doi.org/10.1007/s11831-016-9194-z
33.
ZhaoYWangPCaiS, et al. (2024) ‘Automated fatigue crack detection of orthotropic steel decks using an improved mask region-based convolutional neural network approach’. Advances in Structural Engineering27(1): 17–34. https://doi.org/10.1177/13694332231213460
