A Novel Approach for Predicting Disease in Plant Using Hybrid Deep Convolutional Neural Network

Abstract

Agriculture is the most important sector in Indian economy. Plant disease detection is the major challenge in the agriculture sector. An accurate and a faster detection of diseases in plants which substantially reducing economic losses. Manual monitoring of the plant leaf disease is very critical task and also it is time consuming too. So the automated solution is necessary for plant disease identification. Now-a-days deep learning is becoming the standard technique for image classification. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection. Already few architecture has been developed by the researchers for efficient classification plant disease which includes Faster Region-based Convolutional Neural Network(Faster R-CNN), Region-based Fully Convolutional network(R-FCN), and Single Shot Multibox Detector(SSD). Alex Net, Google Net and VGG-16 are the well knows Deep Convolutional Neural Network architecture for general Image classification. But these architecture does not perform well, when multiple diseases affecting the same leaf. To overcome this, A Hybrid Deep Convolutional Neural Network architecture with segmentation is proposed in this research work which comprises of five convolutional layer, five pooling layer and two fully connected layer. Deep convolutional Neural Networks are most commonly used to analyze visual imagery and are frequently working behind the scenes in image classification. In the proposed system of the Faster-RCNN the input images are feed to the CNN, it will increase the accuracy of images to predict the diseases from the plant leaf.