Plant Disease Detection using Convolutional Neural Networks

Crop production plays a significant role in the agricultural sector. The loss of food is primarily attributed to contaminated crops, which reflexively decreases the rate of development. The detection of plant disease within the field of agriculture is extremely difficult. When identification is incorrect then the assembly of the product and the market's economic value will suffer a significant loss. This research involves a new approach to model identification of plant diseases growth using large, convolution networks, based on the classification of the leaf image. Novel approach and technique used to promote the easy and simple implementation of the program in observance. The developed model can identify thirteen completely different kinds of plant diseases from healthy leaves, with the flexibility to tell apart from the surrounding plant leaves. This technique for the identification of diseases was projected for the first time according to our knowledge. All necessary steps were taken by agricultural consultants to incorporate this disease recognition model, beginning with the collection of photographs to make details. Python & PyCham are used to do the deep CNN process.