A Novel Neural Networks-Based Texture Image Processing Algorithm for Orange Defects Classification

In this paper is proposed, implemented and evaluated a novel radial basis probabilistic neural network (RBPNN) based classification algorithm for classification fruit surface defects in color and texture of a very important fruit as orange. The proposed algorithm takes orange images as inputs then the texture and gray features of defect area are extracted by computing a gray level cooccurrence matrix and the defect areas are classified through an RBPNN-based classifier. The conducted experiments and the results reveal as the classification accuracy achieved is up to 88%.