Accurate Fruits Fault Detection in Agricultural Goods using an Efficient Algorithm

Abstract

The main purpose of this paper was to introduce an efficient algorithm for fault identification in fruits images. First, input image was de-noised using the combination of Block Matching and 3D filtering (<em>BM3D</em>) and Principle Component Analysis (<em>PCA</em>) model. Afterward, in order to reduce the size of images and increase the execution speed, refined Discrete Cosine Transform (<em>DCT</em>) algorithm was utilized. Finally, for segmentation, fuzzy clustering algorithm with spatial information was applied on the compressed image. Implementation results in <em>MATLAB</em> environment and based on the gathered data by the author showed that the proposed algorithm contains a good capability in de-noising. Also, in the proposed method, identification accuracy of faulty regions in fruit was higher than other methods. The major advantage of the proposed method was its high speed which makes it appropriate for real time applications.