Hierarchical Loss Constraint Filter for Low-Visibility Tiny Crack Detection

Tiny crack detection plays a vital role in ensuring the safety of critical industrial components and infrastructure, providing early intervention to prevent crack propagation and mitigate potential damage. Although machine vision-based defect detection has been greatly utilized in safety inspection and maintenance, tiny crack detection remains a big issue due to the low visibility and weak features with large background noise. To address this challenge, this paper presents an end-to-end trainable hierarchical constrained neural network for tiny crack detection. Firstly, we present a hierarchical loss constraint Filter (HLCF) module based on a region-level attention mechanism to capture the holistic vein structure of cracks and enhance the faint feature extraction of tiny cracks. In order to balance local high contrast and holistic crack features, a feature fusion loss constraint is designed to reduce noise interference and refine the boundary details of cracks by learning different receptive fields in each layer. Besides that, we created a dataset consisting of tiny crack samples collected through image processing and manual labeling from industrial production, named TinyCrack. The proposed HLCF model is evaluated on TinyCrack and seven public databases. The experimental indices show that the model achieves Precision over 0.62%, Recall over 0.12%, F-score over 0.53%, and IOU over 1.12% in TinyCrack, demonstrating the best accuracy compared with other public crack detection models. The results indicate that the HLCF detection model has better performance in identifying low-visibility tiny cracks. Note to Practitioners—The motivation for this article stems from the need to develop a high-performance method of detecting tiny cracks for the safety of critical industrial components and infrastructure. Recognition Methods based on image deep learning are widely used in detecting surface cracks due to their good performances of automatically learning features and nonlinear maps. However, the detection performance of tiny cracks, as the original of coarse cracks, is not guaranteed and the attention discrepancies among coarse, thin, and tiny cracks are neglected. To enhance the detection performance of tiny cracks, we propose the deep learning structure-based HLCF model. It concentrates on exploring the selectivity between different crack regions and non-crack regions through dynamically querying in a coarse-to-fine manner. By balancing the crack classes, the model achieves better detection of tiny cracks without the loss of features of coarse cracks. The model provides a feasible way of automatic quality inspection for the safety of important infrastructures such as high-pressure vessels, bridges, and die-cast components.