Enhancing Chickpea Disease Detection Using Hybrid Deep Learning Models

Abstract

For sustainable farming methods and maximum crop yield, early and precise identification of plant diseases is essential. A major agricultural crop, chickpeas (Cicer arietinum) are extremely prone to a number of bacterial, viral, and fungal diseases that significantly lower quality and productivity. In order to effectively extract and classify features, this study suggests a hybrid deep learning model that combines the advantages of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). To identify impacted areas, high-resolution photos of chickpea leaves are prepared using segmentation, contrast enhancement, and noise reduction. In contrast to traditional CNN or single-model architectures, the hybrid model achieves superior precision and accuracy by combining spatial and contextual learning to accurately distinguish between healthy and diseased samples. Results from experiments show better classification. Improved classification accuracy, lower false detection rates, and quicker training collaboration are all shown by the experimental results. Early diagnosis of chickpea diseases is made possible by the suggested system, which gives farmers and agricultural specialists an honest decision-support tool for quick action, disease control, and yield maintenance.