Multiclass Fruit Classification of RGB-D Images Using Color and Texture Feature

Fruit classification under varying pose is still a complicated task due to various properties of numerous types of fruit. In this paper we propose fruit classification method with a novel descriptor as a combination of color and texture feature. Color feature is extracted from segmented fruit image using Color Layout Descriptor, while texture feature is extracted using Edge Histogram Descriptor. Support Vector Machine (SVM) with linear and RBF kernel is used as classifier with 10-fold cross validation. The experimental results demonstrated that our descriptor achieves classification accuracy of over 93.09 % for fruit subcategory and 100 % for fruit category from over 4200 images in varying pose.