Image segmentation method of surface detects based on Gabor filter

To pick-up the surface detects of apple effectively, this paper puts forward a texture segmentation method which is based on the combination of Gabor filter and fuzzy clustering method. First,fuzzy clustering is used to segment defect areas, then Gabor filter is used to convert texture image of defect areas from airspace into the joint space frequency domain, and the characteristic parameters in energy sense are defined, then, in order to decrease the dimension of features, the principal components analysis method is used; finally, in order to achieve the purpose of apple grading,fuzzy clustering is used to texture feature vector which dimension have reduced to recognition the types of defect and calculate the area of defect.. The results show that the method is validated.