Accurate Image Recognition of Plant Diseases Based on Multiple Classifiers Integration

摘要

In agriculture, early detection of plant diseases is essential to avoid irretrievable damage to crops. However, accurate plant disease diagnosis is usually performed by professionals with high precision instruments which is both expensive and time consuming. To tackle this problem, an image recognition method based on multiple classifier integration is described. The method is composed of three parts. Firstly, a public dataset of diseased and healthy plant leaves is adopted. Secondly, three types of convolutional neural network (CNN) models are fine tuned to classify different diseases of plants and evaluated separately. Finally, the three models are integrated and evaluated for accurately diagnosing plant diseases. Experiment result shows the correctness and efficiency of the approach with a best accuracy of 99.92% on split test set.