标题：Glassware Crack Defects Detection Based on Wavelet Transform
作者：Tian, Baozhong; Xu, Shengnan; Li, Zhenhua
作者机构：[Tian, Baozhong; Li, Zhenhua] Shandong Univ, Sch Control Sci & Engn, Jinan 250000, Shandong, Peoples R China.; [Xu, Shengnan] Jinan Presch Educ Coll 更多
会议名称：Chinese Automation Congress (CAC)
会议日期：OCT 20-22, 2017
来源：2017 CHINESE AUTOMATION CONGRESS (CAC)
关键词：defects detection; local adaptive threshold segmentation; wavelet; transform
摘要：An algorithm for detecting and extracting crack defects in glassware using wavelet transform is proposed in this paper. Firstly, the canny image segmentation and the local adaptive dynamic threshold segmentation are carried out on the glassware image with unobvious crack defects. Then, the wavelet decomposition is applied separately on the segmented images. And finally the wavelet fusion is used to extract the crack defects. Experiments show that the proposed algorithm works well in detecting glassware crack defects.