基于语义分割的钢材缺陷检测算法

Steel defect detection algorithm based on semantic segmentation

针对语义分割算法在钢材缺陷检测的实际应用与研究较少,以及传统语义分割方法对缺陷分割精度较低的情况,提出基于HRNet(High-Resolution Net)的钢材表面缺陷深度高分辨率特征检测方法。该方法采用多级网络并联架构保持高分辨率特征,通过并行多分辨率卷积和重复多分辨率融合机制提取强位置敏感度的高分辨率特征,结合HRNet对增强数据集进行冻结训练与迁移学习,最终实现钢材表面缺陷图像的高精度分割。试验表明,该方法对钢材缺陷具有较好的分割效果,其平均交并比(MIOU)指标和平均像素精度(MPA)指标分别达到94.92%和97.64%。

This article proposes a high-resolution feature detection method for steel surface defects based on HRNet(High Resolution Net)to address the limited practical application and research of semantic segmentation algorithms in steel defect detection,as well as the low accuracy of traditional semantic segmentation methods in defect segmentation,The method adopts a multi-level network parallel framework to maintain high-resolution features,extracts high-resolution features with strong position sensitivity through parallel multi-resolution convolution and repeated multi-resolution fusion mechanisms,and combines HRNet to perform freeze training and migration learning on the enhanced dataset,ultimately achieving high-precision segmentation of steel surface defect images,The experiment shows that this method has a good segmentation effect on steel defects,with an average intersection to union ratio(MIOU)index and an average pixel accuracy(MPA)index of 94.92%and 97.64%,respectively.