CFF-Net: Cross-Hierarchy Feature Fusion Network Based on Composite Dual-Channel Encoder for Surface Defect Segmentation
Open Access
- 28 November 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (23) , 4714
Abstract
In industries spanning manufacturing to software development, defect segmentation is essential for maintaining high standards of product quality and reliability. However, traditional segmentation methods often struggle to accurately identify defects due to challenges like noise interference, occlusion, and feature overlap. To solve these problems, we propose a cross-hierarchy feature fusion network based on a composite dual-channel encoder for surface defect segmentation, called CFF-Net. Specifically, in the encoder of CFF-Net, we design a composite dual-channel module (CDCM), which combines standard convolution with dilated convolution and adopts a dual-path parallel structure to enhance the model’s capability in feature extraction. Then, a dilated residual pyramid module (DRPM) is integrated at the junction of the encoder and decoder, which utilizes the expansion convolution of different expansion rates to effectively capture multi-scale context information. In the final output phase, we introduce a cross-hierarchy feature fusion strategy (CFFS) that combines outputs from different layers or stages, thereby improving the robustness and generalization of the network. Finally, we conducted comparative experiments to evaluate CFF-Net against several mainstream segmentation networks across three distinct datasets: a publicly available Crack500 dataset, a self-built Bearing dataset, and another publicly available SD-saliency-900 dataset. The results demonstrated that CFF-Net consistently outperformed competing methods in segmentation tasks. Specifically, in the Crack500 dataset, CFF-Net achieved notable performance metrics, including an Mcc of 73.36%, Dice coefficient of 74.34%, and Jaccard index of 59.53%. For the Bearing dataset, it recorded an Mcc of 76.97%, Dice coefficient of 77.04%, and Jaccard index of 63.28%. Similarly, in the SD-saliency-900 dataset, CFF-Net achieved an Mcc of 84.08%, Dice coefficient of 85.82%, and Jaccard index of 75.67%. These results underscore CFF-Net’s effectiveness and reliability in handling diverse segmentation challenges across different datasets.Keywords
Funding Information
- National Natural Science Foundation of China (62102227, LTGC23E050001, LTGS23E030001, LZY24E050001, ZCLTGS24E0601, 2023K221)
- Joint Fund of Zhejiang Provincial Natural Science Foundation of China (62102227, LTGC23E050001, LTGS23E030001, LZY24E050001, ZCLTGS24E0601, 2023K221)
- Science and Technology Major Projects of Quzhou (62102227, LTGC23E050001, LTGS23E030001, LZY24E050001, ZCLTGS24E0601, 2023K221)
This publication has 40 references indexed in Scilit:
- MPEDA-Net: A lightweight brain tumor segmentation network using multi-perspective extraction and dense attentionBiomedical Signal Processing and Control, 2024
- MMUNet: Morphological feature enhancement network for colon cancer segmentation in pathological imagesBiomedical Signal Processing and Control, 2024
- MGF‐net: Multi‐channel group fusion enhancing boundary attention for polyp segmentationMedical Physics, 2023
- RETRACTED ARTICLE: SCTV-UNet: a COVID-19 CT segmentation network based on attention mechanismSoft Computing, 2023
- Quaternion discrete orthogonal Hahn moments convolutional neural network for color image classification and face recognitionMultimedia Tools and Applications, 2023
- An EffcientNet-encoder U-Net Joint Residual Refinement Module with Tversky–Kahneman Baroni–Urbani–Buser loss for biomedical image SegmentationBiomedical Signal Processing and Control, 2023
- CEDRNN: A Convolutional Encoder-Decoder Residual Neural Network for Liver Tumour SegmentationNeural Processing Letters, 2022
- EE-Net: An edge-enhanced deep learning network for jointly identifying corneal micro-layers from optical coherence tomographyBiomedical Signal Processing and Control, 2022
- Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural networkBiomedical Signal Processing and Control, 2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015