Indonesian fruits classification from image using MPEG‐7 descriptors and ensemble of simple classifiers

Abstract

AbstractFruits classification from image is a very challenging task, particularly for Indonesian indigenous fruits, due to some similarities occurred in several types of the fruits. This study proposes a method to classify Indonesian fruits from image using MPEG‐7 color and texture descriptors. The descriptors were directly extracted from the image without pre‐processing and segmentation steps. Principle component analysis was then applied to reduce the dimension of the descriptors. Four simple classifiers, decision tree, naïve Bayesian, linear discriminant analysis, and k‐nearest neighbor were used to classify the fruit image based on extracted descriptors. An ensemble of simple classifiers trained with some combination of MPEG‐7 descriptors has been constructed to increase the classification accuracy of single simple classifier. To validate the proposed method, an Indonesian fruit images data set consisted of 15 classes was developed in this study. The experiment result showed that the ensemble of simple classifiers achieved the best accuracy of 97.80% by employing linear discriminant analysis, and k‐nearest neighbor as base classifiers trained using CSD, SCD, and the combination of CLD and EHD. Therefore, the proposed method achieved a good classification accuracy and can be applied in vision‐based classification system in industry.Practical ApplicationsThis study proposes a method to classify Indonesian fruits from image using MPEG‐7 descriptors and the ensemble of simple classifiers. The proposed method can be applied in vision‐based fruit sorting system in fruit industry as well as vision‐based fruit pricing system in supermarket.