Defects segmentation on 'Golden Delicious' apples by using colour machine vision

A method based on colour information is proposed to detect defects on 'Golden Delicious' apples. In a first step, a colour model based on the variability of the normal colour is described. To segment the defects, each pixel of ail apple image is compared with the model. If it matches the pixel, it is considered as belonging to healthy tissue, otherwise as a defect. Two other steps refine the segmentation, using either parameters computed on the whole fruit, or values computed locally. Some results are shown and discussed. The algorithm is able to segment a wide range of defects. (C) 1998 Elsevier Science B.V. All rights reserved.