A novel deep convolutional neural network algorithm for surface defect detection

过度拟合 卷积神经网络 计算机科学 人工智能 特征(语言学) 算法 棱锥(几何) 深度学习 特征提取 人工神经网络 模式识别(心理学) 卷积(计算机科学) 一般化 过程(计算) 数据挖掘 数学 语言学 操作系统 数学分析 哲学 几何学
作者
Dehua Zhang,Xinyuan Hao,Linlin Liang,Wei Liu,Chunbin Qin
出处
期刊:Journal of Computational Design and Engineering [Oxford University Press]
卷期号:9 (5): 1616-1632 被引量:37
标识
DOI:10.1093/jcde/qwac071
摘要

Abstract The surface defect detection (SDD) problem is one of the crucial techniques during production process, so it has become a key research area to control the quality of industrial products, which has been increasingly of greater interest to the researchers especially with the rapid development of artificial neural networks technology in recent years. Therefore, this paper proposes a novel deep convolutional neural network algorithm aiming at SDD. Firstly, a dense cross-stage partial Darknet backbone network is designed for feature extraction by optimizing cross-stage partial Darknet through the idea of dense connections, which can, not only enhance feature reuse but also greatly alleviate the overfitting issue. Secondly, a new cross-stage hierarchy module is presented combining the cross-stage feature fusion strategy and depthwise separable convolution technique for each node of the path aggregated feature pyramid network (PAN). Finally, an efficient channel attention (ECA) mechanism is introduced in PAN to construct a novel ECA PAN. The experimental results on three surface defect datasets show that the mean average precision of this network is 2.63, 5.48, and 1.16$\%$ which is higher than that of the baseline network, respectively. The proposed network outperforms not only the classical models but state-of-the-art models, which indicates the proposed algorithm can achieve higher accuracy and speed with fewer calculation parameters. And what is more, the proposed algorithm also has outstanding generalization ability.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
刚刚
李健应助冯露瑶采纳,获得10
刚刚
刚刚
张朝欣完成签到,获得积分10
刚刚
刚刚
机灵夜云完成签到,获得积分10
1秒前
1秒前
2秒前
3秒前
int0030发布了新的文献求助200
3秒前
yyf完成签到,获得积分10
3秒前
你很棒发布了新的文献求助10
3秒前
4秒前
tree发布了新的文献求助10
5秒前
5秒前
NI伦Ge完成签到,获得积分10
5秒前
ooooo发布了新的文献求助10
5秒前
hhhhh发布了新的文献求助10
5秒前
抹茶发布了新的文献求助10
5秒前
上官若男应助勤恳的醉卉采纳,获得10
6秒前
molihuakai应助烤番薯采纳,获得10
6秒前
十一完成签到,获得积分10
7秒前
shuoshuo完成签到,获得积分20
7秒前
范宇航发布了新的文献求助10
7秒前
7秒前
ankihost发布了新的文献求助10
7秒前
浦肯野发布了新的文献求助10
7秒前
8秒前
小贱牛完成签到,获得积分10
8秒前
NexusExplorer应助阳阳杜采纳,获得10
9秒前
9秒前
在水一方应助阳阳杜采纳,获得10
9秒前
宇宙拿铁完成签到 ,获得积分10
9秒前
Orange应助阳阳杜采纳,获得10
9秒前
杨帆发布了新的文献求助10
9秒前
科研通AI6.3应助阳阳杜采纳,获得10
9秒前
想学习发布了新的文献求助10
9秒前
科研通AI6.1应助阳阳杜采纳,获得150
9秒前
科研通AI6.4应助阳阳杜采纳,获得10
9秒前
科研通AI6.1应助阳阳杜采纳,获得10
10秒前
高分求助中
Adhesion Science: Principles & Practice 1234
Signals, Systems, and Signal Processing 610
Petrology and Plate Tectonics,2025 400
Burger's Medicinal Chemistry and Drug Discovery 400
New directions for experimental lessons in science teaching: Myth, Mystery, Necessity? by Emily K. da Silva Cunha Souto (Author), Flávia Lins Silva (Author) 333
Scientific experimentation in the classroom: Comparison between genetic-Socratic-exemplary teaching and workshop teaching by Ingrid Hofer (Author) 333
Programming for Chemical Engineers Using C, C++, and MATLAB 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 物理 内科学 复合材料 催化作用 物理化学 光电子学 电极 细胞生物学 基因 无机化学
热门帖子
关注 科研通微信公众号,转发送积分 6722174
求助须知:如何正确求助?哪些是违规求助? 8458359
关于积分的说明 18058103
捐赠科研通 5974852
什么是DOI,文献DOI怎么找? 2996637
邀请新用户注册赠送积分活动 1972725
关于科研通互助平台的介绍 1926781