Identification and Classification of Normal and Infected Apples using Neural Network

In this paper we have discuss apple recognition techniques of normal and infected. These techniques are, based upon entropy, shape of apple, color, and boundary attributes extraction. Different apple images may have same or different color and shape values, but the infected apples are some different features. Apple recognition system has been proposed, features analysis are color-based, entropy-based, shape based, size-based and boundary analysis in order to increase accuracy of recognition of normal and infected apples. I have used neural network pattern reorganization tool in image processing. Proposed method classifies and recognizes apple images based on obtained features values by using two-layer feed-forward network, with sigmoid hidden and output neurons. The toolbox supports feed forward networks, radial basis networks, dynamic networks, self-organizing maps, and other proven network paradigms. This work represents the MATLAB 7.8.0 software and the recognition of generated signals by artificial neural network technique. . The experimentally it is proved that image processing method for measuring normal and infected apple is accurate and strong practicability with small relative error