Fabric defect inspection is necessary and essential for quality control in the textile\nindustry. Traditionally, fabric inspection to assure textile quality is done by humans,\nhowever, in the past years, researchers have paid attention to PC-based automatic inspection\nsystems to improve the detection efficiency. This paper proposes a novel automatic\ninspection scheme for the warp knitting machine using smart visual sensors. The proposed\nsystem consists of multiple smart visual sensors and a controller. Each sensor can scan\n800 mm width of web, and can work independently. The following are considered in dealing\nwith broken-end defects caused by a single yarn: first, a smart visual sensor is composed of a\npowerful DSP processor and a 2-megapixel high definition image sensor. Second, a wavelet\ntransform is used to decompose fabric images, and an improved direct thresholding method\nbased on high frequency coefficients is proposed. Third, a proper template is chosen in a\nmathematical morphology filter to remove noise. Fourth, a defect detection algorithm is\noptimized to meet real-time demands. The proposed scheme has been running for six months\non a warp knitting machine in a textile factory. The actual operation shows that the system is\neffective, and its detection rate reaches 98%.
Loading....