复杂环境下的冰箱金属表面缺陷检测

doi:10.11772/j.issn.1001-9081.2020060964

计算机应用 ›› 2021, Vol. 41 ›› Issue (1): 270-274.DOI: 10.11772/j.issn.1001-9081.2020060964

所属专题：第八届中国数据挖掘会议(CCDM 2020)

• 第八届中国数据挖掘会议(CCDM 2020) • 上一篇下一篇

复杂环境下的冰箱金属表面缺陷检测

袁野^1,2,3, 谭晓阳^1,2,3

1. 南京航空航天大学计算机科学与技术学院, 南京 211106;
2. 模式分析与机器智能工业和信息化部重点实验室(南京航空航天大学), 南京 211106;
3. 软件新技术与产业化协同创新中心, 南京 211106

收稿日期:2020-05-31 修回日期:2020-08-07 出版日期:2021-01-10 发布日期:2020-11-12
通讯作者: 袁野
作者简介:袁野(1996-),男,湖南岳阳人,硕士研究生,主要研究方向:机器视觉、目标检测;谭晓阳(1971-),男,重庆人,教授,博士,CCF会员,主要研究方向:人脸识别、模式识别、计算机视觉、机器学习。
基金资助:
国家自然科学基金资助项目（61732006，61672280，61976115）；全军共用信息系统装备预研项目（315025305）。

Defect detection of refrigerator metal surface in complex environment

YUAN Ye^1,2,3, TAN Xiaoyang^1,2,3

1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing Jiangsu 211106, China;
2. MIIT Key Laboratory of Pattern Analysis and Machine Intelligence(Nanjing University of Aeronautics and Astronautics), Nanjing Jiangsu 211106, China;
3. Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing Jiangsu 211106, China

Received:2020-05-31 Revised:2020-08-07 Online:2021-01-10 Published:2020-11-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61732006, 61672280, 61976115), the Project of Pre-research on Military Shared Information System Equipment (315025305).

摘要/Abstract

摘要： 为了提升冰箱金属表面的缺陷检测效率，从而应对复杂的生产情况，提出了Metal-YOLOv3模型。使用随机参数变换，将缺陷数据进行了数百倍的扩充，改变原有YOLOv3模型的损失函数，引入了基于完整交并比（CIoU）所设计的CIoU损失函数，用缺陷的分布特性来降低非极大值抑制算法的阈值，并基于K均值聚类算法计算出更适合数据特点的先验框（anchors）值以提升检测精度。在一系列的实验后，发现Metal-YOLOv3模型在检测速度上远胜于主流的区域卷积神经网络（R-CNN）模型，每秒传输帧数（FPS）达到7.59，是Faster R-CNN的14倍，而且平均精确度（AP）也达到了88.96%，比Faster R-CNN高11.33个百分点，说明所提模型同时具备良好的鲁棒性与泛化性能。可见该方法具备有效性，能实际应用于金属制品的生产。

关键词: 金属表面, 缺陷, 冰箱, 损失函数, YOLOv3, 完整交并比

Abstract: In order to improve the efficiency of detecting defects on the metal surface of refrigerators and to deal with complex production situations, the Metal-YOLOv3 model was proposed. Using random parameter transformation, the defect data was expanded hundreds of times; the loss function of the original YOLOv3 (You Only Look Once version 3) model was changed, and the Complete Intersection-over-Union (CIoU) loss function based on CIoU was introduced; the threshold of non-maximum suppression algorithm was reduced by using the distribution characteristics of defects; and the anchor value that is more suitable for the data characteristics was calculated based on K-means clustering algorithm, so as to improve the detection accuracy. After a series of experiments, it is found that the Metal-YOLOv3 model is far better than the mainstream Regional Convolutional Neural Network (R-CNN) model in term of detection speed with the Frames Per Second (FPS) reached 7.59, which is 14 times faster than that of Faster R-CNN, and has the Average Precision (AP) reached 88.96%, which is 11.33 percentage points higher than Faster R-CNN, showing the good robustness and generalization performance of the proposed model. It can be seen that this method is effective and can be practically applied to the production of metal products.

Key words: metal surface, defect, refrigerator, loss function, YOLOv3 (You Only Look Once version 3), Complete Intersection-over-Union (CIoU)

中图分类号:

TP391.4

袁野, 谭晓阳. 复杂环境下的冰箱金属表面缺陷检测[J]. 计算机应用, 2021, 41(1): 270-274.

YUAN Ye, TAN Xiaoyang. Defect detection of refrigerator metal surface in complex environment[J]. Journal of Computer Applications, 2021, 41(1): 270-274.

参考文献

[1] GIRSHICK R,DONAHUE J,DARRELL T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2014:580-587.
[2] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017, 39(6):1137-1149.
[3] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposal networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2015:91-99.
[4] HE K,GKIOXARI G,DOLLÁR P,et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:2980-2988.
[5] LIU W,ANGUELOV D,ERHAN D,et al. SSD:single shot multibox detector[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9905. Cham:Springer, 2016:21-37.
[6] REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:779-788.
[7] REDMON J, FARHADI A. YOLOV3:an incremental improvement[EB/OL].[2020-04-08]. https://arxiv.org/pdf/1804.02767.pdf.
[8] UIJLINGS J R R,VAN DE SANDE K E A,GEVERS T,et al. Selective search for object recognition[J]. International Journal of Computer Vision,2013,104(2):154-171.
[9] LIN T Y,DOLLÁR P,GIRSHICK R,et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:936-944.
[10] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[11] 严刚. 激光声表面波用于金属表面缺陷无损检测的研究[D]. 南京:南京理工大学,2007:11.(YAN G. Laser-generated surface acoustic waves technology for nondestructive detection of surface-breaking defects on metal[D]. Nanjing:Nanjing University of Science and Technology,2007:11.)
[12] 张颖志. 基于激光超声技术的金属表面缺陷检测研究[D]. 大连:大连理工大学,2015:9.(ZHANG Y Z. Study of detecting the metal surface defects based on laser ultrasound technology[D]. Dalian:Dalian University of Technology,2015:9.)
[13] 郝培培. 金属材料超声缺陷检测关键技术研究及应用[D]. 南京:南京信息工程大学,2013:7-8.(HAO P P. Research and application on key technology of metal materials ultrasonic flaw detection[D]. Nanjing:Nanjing University of Information Science and Technology,2013:7-8.)
[14] 刘辉. 激光超声表面缺陷检测机理研究[D]. 太原:中北大学, 2014:22-23.(LIU H. Research on detection mechanism of laser ultrasonic surface defects[D]. Taiyuan:North University of China,2014:22-23.)
[15] 赵海涛. 基于交变磁场测量技术的金属表面缺陷检测系统的研究与实现[D]. 长沙:国防科学技术大学,2004:11.(ZHAO H T. Research and implementation of metal surface defect detection system based on alternating magnetic field measurement technology[D]. Changsha:National University of Defense Technology,2004:11.)
[16] 李光霁, 孙国豪, 潘家祯. 用金属磁记忆方法进行缺陷检测[J]. 华东理工大学学报(自然科学版),2006,32(8):1007-1011.(LI G Q,SUN G H,PAN J Z. Metal magnetic memory testing disfigurement testing rate[J]. Journal of East China University of Science and Technology(Natural Science Edition), 2006,32(8):1007-1011.)
[17] 徐长航, 陈国明, 谢静. 红外图像处理技术在金属表面缺陷检测中的应用[J]. 制造业自动化,2009,31(10):51-54.(XU C H,CHEN G M,XIE J. Application of infrared thermography technology in surface defects detection of products in metal[J]. Manufacturing Automation,2009,31(10):51-54.)
[18] 孔祥伟. 组合光源与图像处理算法在工件表面缺陷检测中的应用[D]. 天津:天津大学,2007:8-9.(KONG X W. The application of combinatorial lamp-house and image processing algorithm in workpiece surface defect inspecting[D]. Tianjin:Tianjin University,2007:8-9.)
[19] 刘源泂. 基于图像处理的钢板表面缺陷成像优化与深度信息提取方法研究[D]. 武汉:武汉科技大学,2011:9-10.(LIU Y J. Research on imaging optimization and depth information extraction method of steel plate surface defects based on image processing[D]. Wuhan:Wuhan University of Science and Technology,2011:9-10.)
[20] 张建川. 红钢棒材表面缺陷图像采集与检测系统研究[D]. 济南:山东大学,2012:12. (ZHANG J C. Study on image acquisition and inspection system for red steel rod surface defects[D]. Jinan:Shandong University,2012:12.)
[21] 张洪涛. 钢板表面缺陷在线视觉检测系统关键技术研究[D]. 天津:天津大学,2008:15.(ZHANG H T. Research on key technology on on-line surface defects detection system for steel plate based on computer vision[D]. Tianjin:Tianjin University, 2008:15.)
[22] 杨铁滨. 基于机器视觉的陶瓷球表面缺陷自动检测技术研究[D]. 哈尔滨:哈尔滨工业大学,2007:11-12.(YANG T B. Ceramic bearing ball surface defects inspection based on computer vision[D]. Harbin:Harbin Institute of Technology, 2007:11-12.)
[23] ZHENG Z,WANG P,LIU W,et al. Distance-IoU loss:faster and better learning for bounding box regression[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto, CA:AAAI Press,2020:12993-13000.
[24] NEUBECK A,VAN GOOL L. Efficient non-maximum suppression[C]//Proceedings of the 18th International Conference on Pattern Recognition. Piscataway:IEEE,2006:850-855.
[25] REDMON J,FARHADI A. YOLO9000:better,faster,stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:6517-6525.

复杂环境下的冰箱金属表面缺陷检测

Defect detection of refrigerator metal surface in complex environment

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	黄继爽, 张华, 李永龙, 赵皓, 王皓冉, 冯春成. 基于动态特征蒸馏的水工隧洞缺陷识别方法[J]. 计算机应用, 2021, 41(8): 2358-2365.
[2]	陈静, 毛莺池, 陈豪, 王龙宝, 王子成. 基于改进单点多盒检测器的大坝缺陷目标检测方法[J]. 计算机应用, 2021, 41(8): 2366-2372.
[3]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[4]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.
[5]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[6]	史杨潇, 章军, 陈鹏, 王兵. 基于轻量级网络的钢铁表面缺陷分类[J]. 计算机应用, 2021, 41(6): 1836-1841.
[7]	蒋宁, 方景龙, 杨庆. 基于单点多盒检测器的全局-局部层级的域适应目标检测[J]. 计算机应用, 2021, 41(2): 517-522.
[8]	张京爱, 王江涛. 基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别[J]. 计算机应用, 2021, 41(1): 275-279.
[9]	聂鑫, 刘文, 吴巍. 复杂场景下基于增强YOLOv3的船舶目标检测[J]. 计算机应用, 2020, 40(9): 2561-2570.
[10]	王思宇, 高炜欣, 李璐. 环口焊X射线焊缝图像质量评定模型[J]. 计算机应用, 2020, 40(9): 2748-2753.
[11]	江金洪, 鲍胜利, 史文旭, 韦振坤. 基于YOLO v3算法改进的交通标志识别算法[J]. 计算机应用, 2020, 40(8): 2472-2478.
[12]	付磊, 任德均, 吴华运, 郜明, 邱吕, 胡云起. 基于改进Fast-SCNN的塑瓶气泡缺陷实时分割算法[J]. 计算机应用, 2020, 40(6): 1824-1829.
[13]	张亚洲, 卢先领. 基于改进相干增强扩散与纹理能量测度和高斯混合模型的导光板表面缺陷检测方法[J]. 计算机应用, 2020, 40(5): 1545-1552.
[14]	杨文霞, 王萌, 张亮. 基于密集连接块U-Net的语义人脸图像修复[J]. 计算机应用, 2020, 40(12): 3651-3657.
[15]	王一婷, 张柯, 李捷, 郝宗波, 段昶, 朱策. 同一场景下超大尺度差异物体的识别和定位方法[J]. 计算机应用, 2020, 40(12): 3520-3525.