Deep Transfer Learning Based Rice Plant Disease Detection Model

In agriculture, plant diseases are mainly accountable for reduction in productivity and leads to huge economic loss. Rice is the essential food crop Asian countries it gets easily affected by different kinds of diseases. Because advent computer vision deep learning (DL) techniques, rice can be detected reduce burden farmers save crops. To achieve this, a new DL based disease diagnosis developed using Densely Convolution Neural Network (DenseNet) with multilayer perceptron (MLP), called DenseNet169-MLP. The proposed model aims classify into three classes namely Bacterial Leaf Blight, Brown Spot, Smut. Initially, preprocessing takes place levels channel separation, grayscale conversion, noise removal median filtering (MF). Then, fuzzy c-means (FCM) segmentation process identifies diseased portion image. pretrained DenseNet169 technique used as feature extractor final layer replaced MLP perform classification. effectiveness has been validated against benchmark dataset simulation outcome examined under diverse measures. obtained results defined superior DenseNet169-MLP over recently presented methods maximum accuracy 97.68%.