AUTOMATIC SURFACE DEFECTS DETECTION ON LEATHERS AND TEXTURED MATERIALS
会议名称：《第七届海内外青年设计与制造科学会议》
会议日期：2006年
学科分类：08[工学] 082204[工学-皮革化学与工程] 0822[工学-轻工技术与工程]
关 键 词：visual inspection leather defect detection wavelet multiresohltion
摘 要：正The visual inspection system was developed for defects detection on leather surfaces, with a very strong focus for the quality control and raw material cutting, an important component of automatic CAD/CAM cutting systems. Leather as a natural material with its variety of visual appearances - nonhomogeneous in color, thickness, brightness, wrinkledness, etc. is a complex object for control and analysis. An efficient algorithm, which combines multiresolution approach, energy and entropy matrices, is presented for detection of defects embedded in leather surface images. A wavelet band selection procedure was developed to automatically determine the number of resolution levels and decompose subimages for the best discrimination of defects and removals of repetitive texture patterns in the image. An adaptive simple binary thresholding is therefore used to separate the defective regions from the uniform gray-level background in the restored image. The proposed methodology can efficiently detect defects even when small features variations are present, and is fast enough to be used for real-time leather inspection.