An Approach to Identify and Classify Agricultural Crop Diseases Using Machine Learning and Deep Learning Techniques

Abstract

Automatic identification of diseases and unhealthy areas in plant leaf pictures and agricultural crop production is made feasible by technology advances that help farmers increase output. Machine learning is used to detect diseases in agricultural harvests., and image processing techniques such as image acquisition., pre-processing., segmentation., feature extraction., Support Vector Machine (SVM), Convolutional Neural Network (CNN), K-Nearest Neighbor, and Gray Level Co-occurrence Matrix (GLCM) are used to identify plant diseases. This method detects plant illness using photos. GLCM extracts textural characteristics from the picture. k-mean clustering segments input images. The SVM classifier boosts the performance of an existing algorithm by dividing the input picture. The approach is to eliminate human participation and enhance farmer procurement. Farmers seldom have a high crop, reducing their revenue. Lack of nutrients, soil dampness, temperature variations, etc. cause this. This analysis approach may use a different technique to improve victimization KNN's accuracy. During this evaluation, we'll develop plant disease prediction tools and propose a novel way to spot unwell plants. The system provides authorized users with information.