Dcmt_Net: Crack Image Segmentation via Dual Frequency-Domain Branches
- 20 April 2026
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (9)
Abstract
Cracks are a ubiquitous and critical form of surface damage in infrastructure; their precise detection and segmentation are paramount for structural safety assessment. To address critical challenges such as feature ambiguity in small-scale cracks, boundary discontinuity, and background interference, this paper proposes Dcmt_Net, a crack segmentation network based on a dual-branch encoder architecture. Specifically, the CNN branch incorporates Fourier frequency-domain enhancement and a Channel-Spatial Group Attention mechanism to bolster edge responses and multi-scale feature modeling. Simultaneously, the Transformer branch integrates Wavelet feature enhancement with a local self-attention structure to effectively capture long-range dependencies and the global continuity of crack images. Furthermore, to achieve efficient complementarity across branches, a Feature Difference Fusion Module is designed to optimize the fusion quality of local and global information. Experimental results on multiple public datasets demonstrate that Dcmt_Net outperforms state-ofthe-art methods. Notably, on the DeepCrack dataset, it achieved 91.46% and 89.13% in key metrics such as RE and F1-score, respectively, validating its robustness and generalization ability in complex crack scenarios.Keywords
This publication has 25 references indexed in Scilit:
- Feature adaptive extraction and gated fusion networks for road crack segmentationEngineering Applications of Artificial Intelligence, 2026
- Hybrid-Segmentor: Hybrid approach for automated fine-grained crack segmentation in civil infrastructureAutomation in Construction, 2025
- An average pooling designed Transformer for robust crack segmentationAutomation in Construction, 2024
- Crack segmentation on steel structures using boundary guidance modelAutomation in Construction, 2024
- A weakly-supervised transformer-based hybrid network with multi-attention for pavement crack detectionConstruction and Building Materials, 2023
- Dual-path network combining CNN and transformer for pavement crack segmentationAutomation in Construction, 2023
- LM-Net: A light-weight and multi-scale network for medical image segmentationComputers in Biology and Medicine, 2023
- A transformer and self-cascade operation-based architecture for segmenting high-resolution bridge cracksAutomation in Construction, 2023
- A crack-segmentation algorithm fusing transformers and convolutional neural networks for complex detection scenariosAutomation in Construction, 2023
- Structural crack detection using deep convolutional neural networksAutomation in Construction, 2022