Structural Crack Image Enhancement: A Review of Techniques for Varied Environmental Conditions

Chunlei Zhao; Sihan Yan; Zhan Zhang; Yuanyuan Cao; Liwei Wu

doi:10.54691/exanfk54

Structural Crack Image Enhancement: A Review of Techniques for Varied Environmental Conditions

Chunlei Zhao, Sihan Yan, Zhan Zhang, Yuanyuan Cao, Liwei Wu

Frontiers in Science and Engineering, (2025), Vol.5, No.12, pp.137-142

Published: December 24, 2025

DOI: 10.54691/exanfk54

PDF: Download Full Text PDF

Abstract

Structural health monitoring is crucial for ensuring the safe operation of civil engineering infrastructure. With the deep integration of computer vision technology and traditional inspection methods, along with the rapid advancement of smart maintenance concepts, image enhancement and quality improvement techniques for crack images captured in complex environments-such as above water, underwater, and in tunnels-have become increasingly important. These images often suffer from issues like blurriness, low contrast, and significant noise interference. By systematically reviewing spatial domain enhancement, frequency domain enhancement, and emerging deep learning-based methods, the core enhancement mechanisms and applicable scenarios of these approaches can be clarified, thereby providing a solid theoretical and technical foundation for intelligent crack identification and automated detection in complex environments in the future.

Keywords: Image Enhancement, Spatial Filtering, Frequency Domain Transform, Deep Learning.

APA Citation: Chunlei Zhao, Sihan Yan, Zhan Zhang, Yuanyuan Cao, Liwei Wu (2025). Structural Crack Image Enhancement: A Review of Techniques for Varied Environmental Conditions. Frontiers in Science and Engineering, 5(12), 137-142. https://doi.org/10.54691/exanfk54

References

HE Shijie. Research and Application of Low-Light Image Enhancement Algorithms[D]. Guilin University of Electronic Technology, 2024. DOI:10.27049/d.cnki.ggldc.2024.000666.
LUO R, QU C M. Research on image enhancement processing of pavement cracks based on improved Retinex algorithm[J]. Journal of Nanyang Institute of Technology, 2016, 8(06): 14-19. DOI:10.16827/j.cnki.41-1404/z.2016.06.004.
ZHUO Qiye. Research on Underwater Image Enhancement and Structural Defect Recognition Based on Deep Learning[D]. Guangzhou University, 2024. DOI:10.27040/d.cnki.ggzdu.2024.000727.
LUO Yaowei, LIU Airong, CHEN Bingcong, et al. Bridge Underwater Structural Crack Detection Based on Image Enhancement and Improved U-net Fusion[J]. Engineering Mechanics, 2025, 42(S1): 276-282+306.
MA Jinxiang, FAN Xinnan, QIAN Chunjun, et al. Underwater Optical Image Enhancement Based on Degradation Characteristic Indicators[J]. Laser & Optoelectronics Progress, 2024, 61(24): 360-373.
LIN C, LIU R F, SU Y, et al. Research on underwater image enhancement and crack quantification driven by deep and transfer learning[J]. Journal of Hydroelectric Engineering, 2025, 44(10): 73-84.
SHEN J T. Research on target recognition algorithm in tunnel low-light environment based on image enhancement[D]. Guilin University of Electronic Technology, 2023. DOI:10.27049/d.cnki.ggldc.2023.000097.
QIAN D S, HAN L X, DING C C, et al. Research on road defect detection based on image enhancement and U-Net[J]. Auto Time, 2025, (21): 193-195.
Zhou L J. A tunnel low-contrast crack extraction method based on image enhancement and watershed segmentation[J]. Computer Science, 2018, 45(S1): 259-261.
Liu J, Xie Q Y, Lyu C S, et al. Research on image quality enhancement method for highway tunnel lining cracks[J]. Journal of Shandong Jianzhu University, 2023, 38(04): 108-116.