A Robust Algorithm for Fruits Recognition System

Abstract

Background: In the last few years, the most popular analysis techniques that have been used for both recognition and classifications of two dimensional (2D) fruits images are based upon color and shape or color and texture or color, size and shape analysis. However, classification of fruits is still a complicated task due to the various properties of numerous types of fruits. These analysis methods are still not robust and effective enough to identify and distinguish fruits images. Materials and Methods: Out of 185 fruit images of eight different fruits collected for the system, (70%) images are used for training and (30%) for testing the system. The system uses the k-Nearest Neighbor (KNN) algorithm as classifier. The proposed method combines four features i.e. color, shape, size and textures. The method classifies and recognizes varieties of fruit images using nearest neighbor’s classification. Results: Accuracy of the proposed system is 97%. The proposed system has the flexibility for many fruits in various colors, shapes and sizes that are captured in different angles and positions. Conclusion: The proposed method is robust, accurate and flexible that can process, analyze, classify and identify the varieties of fruits using their features such as color, shape size and texture. The KNN algorithm is used for fruits recognition which accurately classifies fruit images.