CrackMorph-XAI-Net: A Topology-Preserving and Explainable Framework for Automated Crack Morphology

TL;DR

CrackMorph-XAI-Net is an explainable framework that extracts detailed crack morphology from images, preserving topology and providing measurable features for better structural assessment.

Contribution

The paper introduces a novel, morphology-aware crack analysis framework that maintains topology and offers interpretable structural outputs, extending the CRACK500 benchmark.

Findings

Skeleton extraction achieved a Dice coefficient of 0.991.

Topology preserved in 98.5% of test images.

High correlation (>0.95) between predicted and reference morphology features.

Abstract

Automated crack inspection is increasingly recognized as a critical component of infrastructure monitoring; however, cracks continue to be reported primarily as binary segmentation masks by many current vision-based systems. While localization is facilitated by such masks, limited structural information is provided for robust engineering interpretation. For practical crack assessment, measurable morphological features -- including centerline geometry, branching behavior, junction locations, topology, and severity-related indicators -- are required. In this work, \textit{CrackMorph-XAI-Net}, an explainable morphology-aware framework for image-based crack analysis, is presented. Crack image and region-mask data are converted into a sequence of interpretable structural outputs through four distinct stages: topology-preserving skeleton extraction, junction detection via Gaussian heatmap regression, morphology descriptor computation, and severity-oriented screening. To support rigorous stage-wise evaluation, the standard \textit{CRACK500} benchmark is extended with aligned skeleton maps, junction heatmaps, and topology labels. Experimental validation demonstrates that a mean Dice coefficient of 0.991 is achieved by the learned skeleton extraction stage, with topology preserved in 98.5\% of test images. Furthermore, a recall of 0.964 and an F1-score of 0.887 are obtained in the junction detection stage, highlighting the efficacy of heatmap regression for sparse structural targets. Strong agreement between predicted and reference morphology values is revealed by descriptor-level evaluation, with correlations exceeding 0.95 for length, width, orientation, junction count, and tortuosity.