Plant disease identification: A comparative study

Anthracnose and leaf spot (red rust) are the common diseases affecting the mango plant. Mango being economically important, the detection of these diseases is critical for avoiding epidemics and loss of yield. A machine vision approach has been proposed for plant disease identification using colour images of mango leaves. This approach included using YCbCr converted image and creating a feature vector of textural and colour features of the input images which are fed to the classifier during the testing phase. GLCM, colour based technique and Gabor filter were used for texture and colour feature extraction. Comparison of results obtained using a Minimum distance classifier and using Support Vector Machine (SVM) has been done. Analysis of the feature extraction techniques was performed to obtain individual results for each technique. The overall results gave a classification accuracy of 79.16% and 83.34% for Minimum distance classifier and Support Vector Machine respectively over a database of 86 images.