液晶与显示2025，Vol.40Issue(12)：1853-1867,15.DOI:10.37188/CJLCD.2025-0178
基于改进YOLO11n的导电粒子目标检测算法
Conductive particle target detection algorithm based on improved YOLO11n
摘要
Abstract
To address challenges in detecting defects of conductive particles with varied shapes,uneven sizes,and blurred edges in Flex on Glass(FOG)packaging processes,as well as the inefficiency of manual visual inspection,this paper proposes FSL-YOLO11n,an improved lightweight object detection algorithm based on YOLO11n.The algorithm incorporates the following enhancements:a Feature Complementary Mapping(FCM)module is introduced into the backbone network to reduce parameter redundancy and enhance small object feature extraction through feature splitting,directional transformation,mapping complementarity,and fusion.By introduce medical image boundary processing strategies and dynamic mechanisms,a cross-scale feature dynamic aggregation network is constructed,leading to a new feature pyramid structure named STDA-FPN(Small Target Dynamic Aggregation FPN).This structure incorporates a Selective Boundary Aggregation(SBA)module,DySample module,and DIGC(Dynamic Inception GLU ConvFormer)module to improve multi-scale feature aggregation.A Lightweight Shared Convolutional Quality Detection(LSCQD)head is designed to reduce computational resource consumption and further lightweight the model.Experimental results on a constructed conductive particle dataset show that FSL-YOLO11n reduces the number of parameters by 0.8M compared to YOLO11n,while improving precision,recall,mAP@0.5,and mAP@0.5:0.95 by 2.6%,3%,3.1%,and 2.7%,respectively.It also operates stably on edge devices.The algorithm achieves both lightweight performance and enhanced detection accuracy in experimental settings,providing an efficient and practical solution for industrial inspection applications.关键词
YOLO11/导电粒子/目标检测/特征融合/工业检测Key words
YOLO11/conductive particles/object detection/feature fusion/industrial inspection分类
信息技术与安全科学引用本文复制引用
ZENG Zihao,LIU Peng,DENG Wenjuan,HUANG Jianghua,ZHANG Mingzhi,WANG Zhicheng,PENG Xincun,ZHOU Shumin..基于改进YOLO11n的导电粒子目标检测算法[J].液晶与显示,2025,40(12):1853-1867,15.基金项目
国家自然科学基金(No.61961001,No.62061001) （No.61961001,No.62061001）
江西省自然科学基金(No.20232ACB202004) （No.20232ACB202004）
江西省重大科技研发专项(No.20233AAE02008) （No.20233AAE02008）
抚州市重大"揭榜挂帅"项目(No.2024JCA04)Supported by National Natural Science Foundation of China(No.61961001,No.62061001) （No.2024JCA04）
Natural Science Foundation of Jiangxi Province(No.20232ACB202004) （No.20232ACB202004）
Jiangxi Major Science&Technology R&D Special Project(No.20233AAE02008) （No.20233AAE02008）
Fuzhou Major"Top Talent"Project(No.2024JCA04) （No.2024JCA04）
