An automatic aperture detection system for LED cup based on machine vision

作者：Yang, Yuxiang^*; Lou, Yanting; Gao, Mingyu; Ma, Guojin

来源：Multimedia Tools and Applications, 2018, 77(18): 23227-23244.

DOI：10.1007/s11042-018-5639-8

• Aperturec detection
• Maximum inscribed circle
• Machine vision
• Convolutional neural network

In order to improve the effectiveness of aperture detection and enhance the competitiveness of enterprise, an automatic inspection system for detecting the aperture of Led cup is developed in the paper. The proposed system can achieve detecting the aperture and separating the unqualified Led cups robustly. Specifically, efficient approaches based on three-point circle fitting and convolutional neural network (CNN) are proposed to achieve automatic aperture detection. Then, a novel control unit is designed to separate the unqualified Led cups using the gas claw and air cylinder. Experimental results demonstrate that the detecting accuracy of the developed system can well meet the requirements of manufacturing enterprise. Moreover, the proposed system can greatly save time and labor costs for enterprises. In addition, with this system we can efficiently construct a vision big data of LED cups. Using such a vision big data, problems of the production line can be timely discovered, and the production quality will be greatly improved.

• 出版日期2018-9
• 单位杭州电子科技大学