Leaf Disease Detection Using Ecnnpld As An Augmentative Approach

Abstract

One of the important sectors of Indian Economy is Agriculture. Employment to almost 70% of the countries workforce is provided by Indian agriculture sector. India is known to be the world's largest producer of pulses, rice, wheat, spices and spice products. Farmer's economic growth depends on the quality of the products that they produce, which relies on the plant's growth and the yield they get. Therefore, in field of agriculture, detection of disease in plants plays an instrumental role. Plants are highly prone to diseases that affect the growth of the plant which in turn affects the ecology of the farmer. In order to detect a plant disease at very initial stage, use of automatic disease detection technique is beneficial. The symptoms of plant diseases are conspicuous in different parts of a plant such as leaves, etc. Manual detection of plant disease using leaf images is a tedious job. Hence, it is required to develop computational methods which will make the process of disease detection and classification using leaf images automatic. The widespread development of deep learning has directed to the increasing research interest in image recognition technologies, which enables in the field of computerized image categorization and finding of plant diseases. Farmers are facing huge challenges in cultivation, such as illness. There are a number of leaf diseases that target the rate at which the crop grows.   Appropriate measures on disease identification should be introduced to prevent the issues and minimise the losses. Regular monitoring and authentic disease identification in initial stages of plant growth can increase the quantity and quality of crop yield. Application of technical algorithm correlating the machine vision and mobile vision is actively explored for the sake of achieving the intelligence farming by early plant disease detection. A mobile application is obviously desirable to aid the farmers or garden enthusiasts in diagnosing the sorts of plant ailments. Although some similar applications exist, most of them achieve the function by submitting the image to a team of plant pathologists or expert garden advisors to get possible identification results and some advices. After improving the classification accuracy by using inverted residual block, android application based on image processing and remedy classification techniques used for the detection of plants by observing the symptoms on leaves is presented. The application named as ECNNPLD prediction app turns out to be user friendly to capture the leaf images from mobile camera to process the pre-processing stage, segmentation stage, feature extraction stage and classification stage to predict the diseases.  Proposed research work also trained remedies for classified diseases. Application directly suggests curatives to the farmer for the purpose of crop protection. Further, it also focuses on enhanced convolutional neural network (ECNN) which is one among the CNN based powerful classification techniques.