A Comparison of Optimization Techniques DeepLearning Models Based on Bell Pepper Leaves Diseases Classification

Deep learning has become a powerful tool for classifying and detecting images. In agriculture, deep learning can help organize and predict various issues, such as disease in leaves and stems, providing accurate information to farmers about various plant diseases, etc. This paper explains different optimization techniques used in deep learning, such as Rms prop, SGM, and Adam, specifically in the context of bell pepperdisease classification using Vgg 19. The study aims to analyze and improve the convergence capability of the Vgg 19 deep-learning CNN model. The study aims to determine the optimal configuration that achieves high accuracy in training, validation, and testing for disease classification in bell peppers. The work includes studying different optimizers and learning rates to find the most suitable optimizer and learning rate for the Vgg 19 CNN model in bell pepper leaf disease classification.Based on this study, the paper concludes that the Adam optimizer performs better with a small learning rate.