Deep Learning Techniques Advancements in Apple Leaf Disease Detection

Abstract

An exhaustive and comprehensive investigation was undertaken to address the critical issue of disease detection on apple leaves using cutting-edge deep learning techniques. The research delved into an array of diverse approaches, meticulously examining their efficacy and performance in disease detection, ultimately offering valuable insights into this vital domain. The research effort was marked by the exploration and application of a wide spectrum of deep learning models, each chosen for its distinct characteristics and potential advantages. The results of this extensive work were nothing short of remarkable. This study uses state-of-the-art deep learning techniques to present a thorough and rigorous analysis into the important problem of disease detection on apple leaves. Our research covers a wide range of approaches, all of which have been thoroughly assessed for their efficacy in the diagnosis of disease. We used a wide range of deep learning models, selected for their special qualities and possible benefits. The results of this extensive study are impressive and measurable. VGG-INCEP, the top approach, showed exceptional performance with a measured accuracy rate of 97%. The quantification of precision, recall, and F1 scores were 0.94, 0.92, and 0.92, respectively. Similarly, InceptionV3 yielded an F1 score of 0.93, precision of 0.95, and recall of 0.91, in addition to a measured accuracy of 97%. AlexNet consistently demonstrated measurable high precision (0.95) and recall (0.93), resulting in an F1 score of 0.93, despite a somewhat lower accuracy of 87%. The method's balanced performance is highlighted by these metrics. The study also evaluated the effectiveness of SVM, MobileNet, RCNN, and a recommended method. With quantifiable accuracy of 98% and quantifiable precision, recall, and F1 scores of 0.96, the suggested technique stood out. This assessment unequivocally shows that the suggested approach produces the best accuracy and overall performance and is distinguished by its measured precision and recall balance. It provides a numerical evidence of the method's efficacy in accurately detecting and categorising apple leaf diseases. The findings highlight the disparities in performance across the various models and highlight how the proposed approach, with its quantifiable excellence, has the potential to completely transform apple orchard disease detection.