Plant syndrome recognition by Gigapixel Image using Convolutional Neural Network

Abstract

. The plants play a vital role in our day-to-day life. It is important to monitor the health of the plants. Generally, plant diseases are identified using image processing techniques. In those techniques, the input images of plants are of an only megapixel size. In this method image processing of plants is done using a gigapixel input image that covers the entire area of the crop. To process this huge gigapixel image a method called Neural Image Compression(NIC) is used. The identification of the plant diseases is done using Convolutional Neural Networks(CNN) from the neutrally compressed gigapixel image. CNN is trained using a probability estimation algorithm to identify the affected portion of the plant crop.