Apple defect detection using statistical histogrambased Fuzzy C-means algorithm

Image segmentation is one of the important andcomplicated processes among image processing and computervision algorithm. Its purpose is to partition an input image intodisjoint parts. In this article an important application of imageprocessing in determination of apple quality is studied, and anautomatic algorithm is proposed in order to determine applesskin color defects. First, this image is converted from RGB tocolor space L*a*b*. Then fruit shape is extracted by ACMalgorithm. Finally, the image has segmented using SHFCMalgorithm. Experimental results on the acquired images showthat both FCM and SHFCM spend the same iterations toaccomplish the segmentation process and get the same results.However, the proposed SHFCM algorithm consumes less timethan the standard FCM algorithm. Accuracy of the proposedalgorithm on the acquired images is 91% and 96% for healthypixels and defected ones, respectively.

Apple defect detection using statistical histogrambased Fuzzy C-means algorithm Keywords:

Image segmentation , apple defects , colorspace , statistical histogram , fuzzy c-means algorithm , active counter model