IMAGE-PROCESSING TECHNIQUES FOR LEATHER HIDE RANKING IN THE FOOTWEAR INDUSTRY

The subjective assessment of finished leather hide has resulted in muc h argument, wasted costs and disruption of production schedules in bot h the tannery and leather footwear industry. Leather has attracted muc h research work worldwide; however, to date no objective quality asses sment methodology is available, let alone an automatic assessment syst em. In this project, a machine-vision-based approach to grading leathe r hide has been developed. The image of a given castle hide was acquir ed using the developed machine vision system. A map of the different t ypes of defect contours contained in the hide was extracted. Algorithm s were then formulated enabling the computerization of the quarter rul e, a standard method for grading leather hide in the footwear industry . Typical results from the developed grading process include the leath er cuttable areas within a given hide, taking into account various typ es of defects, and the contour map of defects, which in fact is a vita l input to any computerized shoe-part nesting system. The success of a utomatically grading leather hide in this project will not only provid e the tanner with a means of accurately defining the price of a leathe r hide but also greatly assist the footwear manufacturer in the optima l nesting of irregular shoe parts within a given hide.