Non-concentric Circular Texture Removal for Workpiece Defect Detection

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Non-concentric Circular Texture Removal for Workpiece Defect Detection
	Qin SJ(秦书嘉)2,3; Guo, Di 2; Chen, Heping 2
	2019
会议日期	August 8-11, 2019
会议地点	Shenyang, China
关键词	Defect detection Non-concentric circle Small dataset
页码	576-584
英文摘要	Since workpiece defect detection is a typical problem in computer vision with small datasets, generally its solutions cannot exploit the advantages of high accuracy, generalization ability, and neural network structures from the deep learning paradigm. Thus, traditional image processing techniques are still widely applied in such requirements. Aiming at three types of defects (crack, pitting and scratch) on a workpiece with non-concentric circular textures that severely interfere in the defect recognition stage, this paper proposes a sliding window filter for the texture detection. Experiments compare the proposed method with the polar coordinate mapping method and the T-smooth texture removal algorithm. Results show that the proposed method reveals the three types of defects better than the other two methods.
产权排序	1
会议录	Intelligent Robotics and Applications - 12th International Conference, ICIRA 2019, Proceedings
会议录出版者	Springer Verlag
会议录出版地	Berlin
语种	英语
ISSN号	0302-9743
ISBN号	978-3-030-27537-2
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/25501]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Qin SJ(秦书嘉)
作者单位	1.The University of Hong Kong, Pok Fu Lam, Hong Kong 2.Shenzhen Academy of Robotics, Shenzhen 518000, China 3.Shenyang Institute of Automation, CAS, Shenyang 110000, China
推荐引用方式 GB/T 7714	Qin SJ,Guo, Di,Chen, Heping. Non-concentric Circular Texture Removal for Workpiece Defect Detection[C]. 见:. Shenyang, China. August 8-11, 2019.