Plant Diseases Detection Based on Color Features and Kapur’s method

Plant diseases have become an important issue because they cause important reduction in each quality and amount of agricultural products. Automatic detection of plant diseases is an important analysis topic because it could significantly help in observation giant fields, and enable automatic detection the symptoms of diseases as soon as they appear on the plant leaves. In this paper an algorithm for plant disease detection using different color models is proposed and tested. Plant leaf images were first transformed into RGB, YCbCr, HSI or CIELAB color model. Noise in transformed image was reduced by applying median filter. At the end, disease spots were detected by using Kapur’s thresholding method. Based on the experimental results, HSI color model is the most suitable for automatic plant disease detection, while RGB is practically unusable.