Identification of leather defects using an autoadaptive edge detection image processing algorithm

This paper presents a novel technique for identifying the defects in leather by using an auto adaptive edge detection algorithm. The Results achieved formally to identify the leather defects by using several edge detection methods are not up to the required standards. Those conventional methods don't exhibit the continuity and clarity of leather defects. This algorithm is thus proposed to define leather edges clearly and continuously. The proposed edge detection algorithm identifies the leather defects and removes the irrelevant edges. The results are compared with other conventional methods such as Prewitts, Sobel, Roberts, Canny and Laplacian methods.