中山大学学报（自然科学版）（中英文）2025，Vol.64Issue(2)：129-137,9.DOI:10.13471/j.cnki.acta.snus.ZR20240261
可在TFT-LCD面板中实现多背景视觉细微缺陷检测的YOLO-DSM方法
YOLO-DSM method for detecting multi-background visual micro-defects in TFT-LCD panels
摘要
Abstract
A deep learning image detection model based on You Only Look Once-Double Spatial-Squeeze Module(YOLO-DSM)is proposed.First,the Hierarchical Mixed-scale Unit(HMU)module is introduced after each Dark module to improve the detection accuracy of target defects on TFT-LCD panels.The original Spatial Pyramid Pooling(SPP)is replaced with Simple Spatial Mlp Attention(SSMA)to enable the network to focus more on targets with low contrast against the background.Second,the Double Spatial-Squeeze Module(DSM)is introduced to help the network enhance useful features and suppress useless ones,thereby enhancing the integration of semantic information.Finally,the Omni-dimensional Dynamic Convolution(ODConv)module replaces the down-sampling convolution of the original network to refine local feature mapping and achieve full extraction of local defect features.In comparative experiments on a self-made TFT-LCD defect dataset,the YOLO-DSM network achieved an mAP accuracy of 97.40%and an FPS of 77.42 frames.This meets the requirements of TFT-LCD defect detection tasks.关键词
视觉细微缺陷/YOLO-DSM/全维动态卷积/SCSE注意力机制Key words
visual micro-defects/YOLO-DSM/omni-dimensional dynamic convolution/spatial and channel squeeze&excitation分类
信息技术与安全科学引用本文复制引用
孔祥飞,王森,赵林,陈明方..可在TFT-LCD面板中实现多背景视觉细微缺陷检测的YOLO-DSM方法[J].中山大学学报（自然科学版）（中英文）,2025,64(2):129-137,9.基金项目
国家自然科学基金(52065035) （52065035）
