Fruit Classification using Neural Network Model

Abstract

Fruit classification process is gaining importance in image processing applications specifically in agricultural area. However, classification process is challenging for images captured in natural environment due to the existence of nonuniform illumination. Different illuminations produce different intensity on the object surface and thus lead to inaccurate classification. Therefore, this study focuses on the improvement of development of classification model for images captured in natural environment. This study has developed a neural network (NN) model that is able to classify objects based on their surface colour. The result of the NN model shows that, with the network configuration of 6-7-4, the NN model works very well for objects exposed to the natural illumination. To justify the proof-of-concept, the proposed classification model is tested on jatropha fruit images and the results show that the developed model is able to classify the fruit accurately.