Chilli Leaf Disease Identification Using Histrogram Equalisation Technique

Sustainable agriculture depends on disease diagnosis and plant monitoring. However, it requires to necessitate prompt and precise diagnosis. Plant diseases are challenging to manually monitor. We propose an efficient method for identifying diseases in chilli leaves in this research. To begin with, high contrast quality images are resized and the RGB components are separated and subjected to histogram equalization. Further, the K means clustering is applied to extract the features. Lastly, data samples for various disease classes are trained using SVM classifiers. Comparing our method to existing techniques, we find that it achieves about 92.85 % precision.