Capsicum Plant Advanced Disease Detection Using CNN-SVM Fusion for Precision Crop Protection

With the use of a combination of cutting-edge deep learning techniques, such as artificial neural networks, convolutional neural networks, and support vector machines, a unique method for disease classification in capsicum plants was introduced in this research study. As a fundamental component of sustainable agriculture, we address the difficult task of correctly diagnosing numerous diseases that threaten capsicum crops. By extracting complex characteristics from pictures of capsicum leaves using CNNs, the methodology enables robust feature representation. SVMs and ANNs are then used to effectively classify diseases using these derived attributes. These models can be combined to accurately identify and classify various illness classifications with excellent recall, accuracy, and F1 scores. Findings, obtained through thorough experimentation and evaluation, show the effectiveness of our suggested strategy, obtaining an overall accuracy of 97%. With precision scores of 91.37%, 89.34%, and 87.52%, respectively, for illnesses like Scherotium Rolfsii, Rhizoctonia solani, and Phomopsis Capsici. The effective use of CNNs, SVMs, and ANNs in disease classification highlights how disruptive disease management in agriculture could become with these technologies. A data-driven approach to early disease diagnosis is provided by the suggested model, allowing for prompt action and better crop protection techniques.