Machine vision tool for real-time defect detection and classification on circular knitting machines by using statistical parameters and Radon Transform

This work presents a new highly automated artificial vision inspection (AVI) tool for real-time defect detection and classification on circular knitting machines based on the combination of statistical analysis, Image Processing and Radon Transform. The tool (software + hardware) is directly attached to a circular knitting machine and the inspection is performed on-line. The automatic inspection allows the detection and classification of the most frequently occurring types of defects on knitted fabrics, which are significant for purposes of quality control and fabric grading. The reliability of the detection tool is about 93% (defect detected vs. effectively existing defects). Key-Words: real time, image processing, knitting machines, skewness, kurtosis, radon transform.