WANG Junxiang, PENG Huacang, HU Honghao, LIU Ying, ZHU Yonghong

(School of Mechanical and Electrical Engineering, Jingdezhen Ceramic Institute, Jingdezhen 333403, Jiangxi, China)

Abstract: Based on the situation that most daily-use ceramic enterprises still adopt manual ceramic quality testing method, this paper proposes an online detection system based on computer vision technology, which mainly includes two modules, i.e. hardware and software modules. The hardware module mainly carries out ceramic products transportation, data acquisition and intelligent control. The software one mainly achieves ceramic defects online detection. By using ceramic outer- boundary extraction, circle center calculation and its stability analysis, the roundness of ceramic boundary can be rapidly determined. The experimental results show that the proposed algorithm can accurately and quickly extract ceramic outer-boundary and judge the corresponding roundness.

Key words: ceramic defects, computer vision technology, roundness detection