Cascaded detection method for surface defects of lead frame based on high-resolution detection images

引线框架 帧(网络) 人工智能 过程(计算) 计算机科学 计算机视觉 帧速率 噪音(视频) 目标检测 管道(软件) 模式识别(心理学) 图像(数学) 材料科学 操作系统 半导体器件 复合材料 程序设计语言 电信 图层(电子)
作者
Tingrui Sun,Zhiwei Li,Xinjie Xiao,Zhihui Guo,Wenle Ning,Tingting Ding
出处
期刊:Journal of Manufacturing Systems [Elsevier BV]
卷期号:72: 180-195 被引量:13
标识
DOI:10.1016/j.jmsy.2023.11.017
摘要

In the field of semiconductor production and manufacturing, the detection of defects on lead frame surfaces is a vital process. This process plays a key role in ensuring the quality of the final product. Using high-resolution detection images to detect multi-scale tiny surface defects is necessary, but this amplifies the impact of environmental noise. Therefore, suppressing both the false negative rate and false positive rate in practical detection scenarios is a challenge that needs to be overcome. Current research on lead frame surface defect detection is mostly concentrated on the downloaded standard original images, which limits its application in actual production lines. This paper presents a cascaded detection method for surface defects of lead frame based on high-resolution detection images. Firstly, this study presents the unit cell extraction module to convert the detection object from high-resolution image to hundreds of unit cells. The proposed module can handle real-time detection images in the production pipeline, especially addressing situations such as lighting imbalances and tilted detection images. Subsequently, this study proposes a lead frame surface defect detection network (LDD-net), which takes unit cells as inputs and can effectively detect multi-scale defects. Compared to other models, LDD-net can effectively capture the features of subtle defects. Additionally, this paper introduces the deviation in the central width direction into the CIoU localization loss, enhancing the accuracy of defect localization in LDD-net. The data set is constructed using the machine vision detection system and conducts training and testing. Specifically, experiments of LDD-net on the data set obtained 85.01% mean average precision (mAP) and 37 ms of inference time, respectively. The detection accuracy exceeds 95%, and the false negative rate can be controlled below 6%. This approach will assist manual monitoring personnel in evaluating product quality.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Eric完成签到,获得积分10
1秒前
开朗的山彤完成签到,获得积分10
1秒前
维生素完成签到,获得积分10
1秒前
时林完成签到,获得积分10
1秒前
傻瓜完成签到 ,获得积分10
2秒前
3秒前
大观天下发布了新的文献求助10
5秒前
忽远忽近的她完成签到 ,获得积分10
5秒前
维生素发布了新的文献求助10
6秒前
butterfly发布了新的文献求助10
8秒前
豆豆完成签到 ,获得积分10
9秒前
范先生完成签到,获得积分10
12秒前
2222222完成签到,获得积分10
12秒前
Hello应助bulingbuling采纳,获得10
12秒前
蜡笔小新完成签到,获得积分10
15秒前
希望天下0贩的0应助小王采纳,获得10
15秒前
赘婿应助lh采纳,获得10
16秒前
16秒前
科研通AI2S应助butterfly采纳,获得10
17秒前
大模型应助butterfly采纳,获得10
17秒前
19秒前
做个梦给你完成签到,获得积分10
19秒前
学霸宇大王完成签到 ,获得积分10
19秒前
甜蜜的楷瑞完成签到,获得积分10
20秒前
魏煜佳完成签到,获得积分10
21秒前
Lc完成签到,获得积分10
21秒前
三伏天完成签到,获得积分10
21秒前
清图完成签到,获得积分10
21秒前
英姑应助简单采纳,获得10
21秒前
爱喝牛奶的大兔子完成签到 ,获得积分20
22秒前
23秒前
23秒前
潇湘雪月完成签到,获得积分10
24秒前
迎南完成签到,获得积分10
24秒前
懒癌晚期完成签到,获得积分10
25秒前
25秒前
初夏微凉发布了新的文献求助10
25秒前
25秒前
26秒前
27秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038388
求助须知:如何正确求助?哪些是违规求助? 3576106
关于积分的说明 11374447
捐赠科研通 3305798
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029