Chickpea disease classification using hybrid method

Chickpea is one of the most important legumes in the world, however, it is prone to various diseases that can significantly reduce its yield and quality. Hence, the accurate classification of these diseases are crucial for effective disease management. In this study, we propose a combined approach for chickpea disease classification using GLCM-Color Histogram features with Bilateral filtering and non-local means filtering. Our research comprises three phases: image preprocessing, feature extraction, and classification. To enhance the model's robustness and reduce noise, we applied Bilateral filtering, non-local means filtering, and data augmentation techniques. We utilized a combination of gray-level co-occurrence matrix (GLCM) and Color Histogram for feature extraction, which can capture the texture and color features important for image classification tasks. The extracted features were then classified using Multi-Layer Perceptrons (MLPs), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RF). The experimental results indicate that the combined features extracted using GLCM and Color Histogram with the SVM classifier outperformed individual feature extractors and classifiers, achieving a testing accuracy of 95.49 %. Our study demonstrates that proper image preprocessing, data augmentation, and feature extraction provide an efficient classification method for identifying and classifying chickpea disease.