Real-time detection system for polishing metal surface defects based on convolutional feature concentration and activation network

增采样 计算机科学 特征(语言学) 人工智能 抛光 模式识别(心理学) 卷积神经网络 计算机视觉 材料科学 图像(数学) 语言学 哲学 复合材料
作者
Zhongliang Lv,Zhenyu Lu,Kewen Xia,Lie Zhang,Hailun Zuo,You-wei Xu,Kang Liu
出处
期刊:Expert Systems With Applications [Elsevier BV]
卷期号:257: 125041-125041 被引量:4
标识
DOI:10.1016/j.eswa.2024.125041
摘要

This study aims to improve the accuracy and efficiency of detecting defects on polished metal surfaces by developing a new detection system. A network model explicitly designed for detecting defects on polished metal surfaces and a convolutional feature concentration and activation network (CFCANet) are proposed in this paper. This model significantly enhances the recognition of tiny defects by introducing a small-target detection head, ensuring high-precision detection results. In addition, the feature concentration and activation (FCA-C2f) module proposed in this study enhances the model's sensitivity to anisotropic features, thereby improving defect detection accuracy. The content-aware reassembly of features (CARAFE) upsampling algorithm is used instead of traditional nearest-neighbour interpolation methods to effectively preserve detailed information and improve the quality and efficiency of upsampling. By optimising the lighting conditions and using composite light source illumination technology, the probabilities of missed detections and false alarms can be reduced. Combined with the CFCANet detection network, the defect detection performance of the proposed method on polished metal surfaces is effectively enhanced. To validate the effectiveness of the proposed method, a new dataset for detecting defects on polished metal surfaces, PMS-DET, was constructed in this study and validated on the NEU-DET dataset. Experimental results show that CFCANet effectively improves the defect detection accuracy on polished metal surfaces, achieving a mAP0.5:0.95 value of 42.4 % on the PMS-DET dataset, an increase of 11.9 %. The model parameters are reduced by 6.7 %, and the detection speed is improved by 28.1 %. Compared with existing detection models, this research method demonstrates significant improvements in detection accuracy, model size and computational efficiency, especially regarding GFLOPs and detection speed, proving its potential application value in practical industrial scenarios.
最长约 10秒,即可获得该文献文件

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
小白完成签到,获得积分10
刚刚
兰德启明发布了新的文献求助30
1秒前
脑洞疼的应助被mx采纳,获得10
1秒前
Zurini发布了新的文献求助30
1秒前
2秒前
embrace完成签到,获得积分10
2秒前
fcc发布了新的文献求助10
3秒前
3秒前
4秒前
4秒前
maxiaole的应助被简单的怀绿采纳,获得10
5秒前
5秒前
ppll3906完成签到,获得积分10
6秒前
小蘑菇的应助被My_magnum_opus采纳,获得10
6秒前
仁爱吐司完成签到,获得积分10
6秒前
所所的应助被My_magnum_opus采纳,获得30
6秒前
赘婿的应助被My_magnum_opus采纳,获得30
6秒前
bkagyin的应助被My_magnum_opus采纳,获得10
6秒前
从容映易完成签到,获得积分10
6秒前
CipherSage的应助被My_magnum_opus采纳,获得30
7秒前
华仔的应助被六六采纳,获得10
7秒前
田様的应助被My_magnum_opus采纳,获得10
7秒前
lx的应助被JXL采纳,获得10
7秒前
7秒前
nan完成签到,获得积分10
7秒前
李子昂发布了新的文献求助10
8秒前
8秒前
Zurini完成签到,获得积分10
9秒前
ww发布了新的文献求助10
10秒前
微笑的豹豹完成签到,获得积分10
10秒前
754753044完成签到,获得积分10
11秒前
辰开心完成签到 ,获得积分10
11秒前
11秒前
ujeec完成签到,获得积分10
12秒前
xiaoming完成签到 ,获得积分10
12秒前
xiaoming完成签到 ,获得积分10
12秒前
12秒前
12秒前
12秒前
ttthe完成签到 ,获得积分10
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8168241
求助须知:如何正确求助?哪些是违规求助? 9561243
关于积分的说明 21760380
捐赠科研通 7759541
什么是DOI,文献DOI怎么找? 3429959
关于科研通互助平台的介绍 2553785
邀请新用户注册赠送积分活动 2474541