FABRIC DEFECT DETECTION AND CLASSIFICATION USING IMAGE-ANALYSIS

Conventional image analysis hardware was used to image solid-shade, un patterned, woven fabrics. Two different software approaches for detect ing and classifying knot and slub defects were studied and compared. T he approaches were based on either gray level statistics or morphologi cal operations. The autocorrelation function was used for both methods to identify fabric structural repeat units, and statistical or morpho logical computations were based on these units. Plain weave and twill weave fabrics were used to compare the performance of each software ap proach.