Abstract
Convolutional Neural Network is the base of all deep learning models. Therefore a Convolutional Neural Network model is created and developed to perform plant disease detection and classification using apple and tomato leaf images of healthy and diseased plants. The model consists of four convolutional layers each followed by pooling layers. Two fully connected dense layers and sigmoid function is used to detect the probability of presence of disease or not. Training of the model was done on apple and tomato leaf image dataset containing 3663 images achieving an accuracy of 87%. The overfitting problem is identified and removed setting the dropout value to 0.2. As the model allows parallel processing, it is also run on GPU Tesla to evaluate its speed of performance and accuracy. Hence the paper provides an insight of creativeness to the researchers to develop an integrated plant disease identification system that gives successful results in realtime.

This publication has 7 references indexed in Scilit: