فهرست نشریات علمی دسترسی آزاد ایران

To minimize losses in the agricultural sector and ensure food security, early diagnosis and identification of sugarcane diseases are essential. Conventional diagnostic approaches are often costly, labor-intensive, and reliant on the subjective expertise of individuals in recognizing pathogenic microorganisms. Recent improvements in machine learning and deep learning provide viable solutions for automating the data analysis and classification of plant diseases through image-based analysis. This study presents a comprehensive analysis of image-based sugarcane disease identification systems, emphasizing various computational techniques to achieve optimal results, and applies these methods in a mobile application. In this study, the authors review relevant case studies, highlighting key developments in disease detection using computer vision technologies, and demonstrating how these approaches improve diagnostic accuracy while enhancing computational efficiency and reducing resource consumption. The authors aim to guide future research and development by offering methods to overcome existing challenges. This assessment serves as a resource for academics and practitioners, providing insights into current practices and suggesting ways to enhance automated plant disease detection systems for mobile and handheld devices.