PLANT DISEASE DETECTION using image processing

By: Shashanka Sekhar Dash

Objective: quick detection of plant diseases using image processing techniques

Every year the plant diseases destroy the produce of farmers and cause a huge loss to the economy . Therefore there is an urgent need to develop a system which can detect the plant diseases at an early stage so that necessary steps can be taken to curb the disease.

This project is one such attempt to detect the diseases and give the results quickly. The model has been trained on large amount of data and hence gives considerable accuracy and has a number of diseases of various crops.

The Project uses Image Processing using Tensorflow and Keras Library in Python. The technique used here is Convolutional Neural Networks which is a part of Machine Learning.

The CNN model used for classification is Alexnet. Alextnet has 5 convolution layers and 3 fully connected layers. It uses Relu as the activation function so this introduces non linearity and solves the vanishing gradient problem. The model gives an accuracy of about 96%.