CNN BASED METHOD FOR MULTI-TYPE DISEASED ARECANUT IMAGE CLASSIFICATION
Main Article Content
Arecanut image classification is a challenging task to the researchers and in this paper a new combined approach of multi-gradient images and deep convolutional neural networks for multi-type arecanut image classification is presented. To enhance the fine details in arecanut images affected by different diseases, namely, rot, split and rot-split, we propose to explore multiple-Sobel masks for convolving with the input image. Although, the images suffer from distortion due to disease infection, this masking operation helps to enhance the fine details. We believe that the fine details provide vital clues for classification of normal, rot, split and rot-split images. To extract such clues, we explore the combination of multi-gradient and AlexNet by feeding enhanced images as input. Implementation results on the four-class dataset indicate that the approach proposed is superior in terms of classification rate, recall, precision and F-measures. The same conclusion can be drawn from the results of comparative study of proposed method with the existing methods.