A Fabric Defect Detection System Based Improved YOLOv5 Detector
Authors:
Open Access
- 1 September 2021
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2010 (1) , 012191
Abstract
Fabric defect detection is a key part of product quality assessment in the textile industry. It is important to achieve fast, accurate and efficient detection of fabric defects to improve productivity in the textile industry. For the problems of irregular shapes and many small objects, an improved YOLOv5 object detection algorithm for fabric defects is propose. In order to improve the detection accuracy of small objects, the ASFF(Adaptively Spatial Feature Fusion) feature fusion method is adopted to improve the PANet’s bad effect on multi-scale feature fusion. The transformer mechanisms can enhance fused features, allowing the network to focus on useful information. Experimental results show that the mean average precision of the improved YOLOv5 object detection algorithm in fabric defect map detection is 71.70%. The improved algorithm can quickly and accurately improve the accuracy of fabric defect detection and the accuracy of defect localization.Keywords
This publication has 3 references indexed in Scilit:
- Fabric defect inspection based on lattice segmentation and Gabor filteringNeurocomputing, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015