Next Article in Journal
A Scalable Sub-Picosecond TDC Based on Analog Sampling of Dual-Phase Signals from a Free-Running Oscillator
Previous Article in Journal
Non-Destructive Characterization of Drywall Moisture Content Using Terahertz Time-Domain Spectroscopy
Previous Article in Special Issue
Streak Tube-Based LiDAR for 3D Imaging
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Unified Preprocessing Pipeline for Noise-Resilient Crack Segmentation in Leaky Infrastructure Surfaces

Department of Electrical Engineering, Soonchunhyang University, Asan 31538, Republic of Korea
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(17), 5574; https://doi.org/10.3390/s25175574 (registering DOI)
Submission received: 30 July 2025 / Revised: 2 September 2025 / Accepted: 5 September 2025 / Published: 6 September 2025

Abstract

Wet cracks caused by leakage often exhibit visual and structural distortions due to surface contamination, salt crystallization, and corrosion byproducts. These factors significantly degrade the performance of sensor- and vision-based crack detection systems. In moist environments, the initiation and propagation of cracks tend to be highly nonlinear and irregular, making it challenging to distinguish crack regions from the background—especially under visual noise such as reflections, stains, and low contrast. To address these challenges, this study proposes a segmentation framework that integrates a dedicated preprocessing pipeline aimed at suppressing noise and enhancing feature clarity, all without altering the underlying segmentation architecture. The pipeline begins with adaptive thresholding to perform initial binarization under varying lighting conditions. This is followed by morphological operations and connected component analysis to eliminate micro-level noise and restore structural continuity of crack patterns. Subsequently, both local and global contrast are enhanced using histogram stretching and contrast limited adaptive histogram equalization. Finally, a background fusion step is applied to emphasize crack features while preserving the original surface texture. Experimental results demonstrate that the proposed method significantly improves segmentation performance under adverse conditions. Notably, it achieves a precision of 97.5% and exhibits strong robustness against noise introduced by moisture, reflections, and surface irregularities. These findings confirm that targeted preprocessing can substantially enhance the accuracy and reliability of crack detection systems deployed in real-world infrastructure inspection scenarios.
Keywords: crack segmentation; deep learning; image preprocessing; infrastructure inspection; wet cracks crack segmentation; deep learning; image preprocessing; infrastructure inspection; wet cracks

Share and Cite

MDPI and ACS Style

Shin, J.-J.; Cho, J. A Unified Preprocessing Pipeline for Noise-Resilient Crack Segmentation in Leaky Infrastructure Surfaces. Sensors 2025, 25, 5574. https://doi.org/10.3390/s25175574

AMA Style

Shin J-J, Cho J. A Unified Preprocessing Pipeline for Noise-Resilient Crack Segmentation in Leaky Infrastructure Surfaces. Sensors. 2025; 25(17):5574. https://doi.org/10.3390/s25175574

Chicago/Turabian Style

Shin, Jae-Jun, and Jeongho Cho. 2025. "A Unified Preprocessing Pipeline for Noise-Resilient Crack Segmentation in Leaky Infrastructure Surfaces" Sensors 25, no. 17: 5574. https://doi.org/10.3390/s25175574

APA Style

Shin, J.-J., & Cho, J. (2025). A Unified Preprocessing Pipeline for Noise-Resilient Crack Segmentation in Leaky Infrastructure Surfaces. Sensors, 25(17), 5574. https://doi.org/10.3390/s25175574

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop