Grading of persimmon fruits into three commercially maturity stages was conducted by image analy-sis technique. An automatic algorithm was developed to classify the fruits based on the external color of them. Physical, mechanical and nutritional properties of fruits were determined to compare theresults of image analysis and visual classification. During the process of image segmentation, the blackspots on persimmon fruits were removed to dilute the effect of them on the features to be extractedand used for classification. Among the features, there were significant differences between maturitystages for mean values of R, G, b*, gray scale and S channels. Two classifiers based on linear (LDA) andquadratic discriminant analysis (QDA) were used to assess the applicability of vision system. The resultsshowed that QDA classifier could be valuable in categorizing the fruits with better overall accuracy rateof 90.24%.