Progresses in Sugarcane Leaf Defect Identification : A Review

Abstract

Sugarcane is a crucial crop for the global sugar industry, but its yield and quality can be significantly impacted by various leaf defects. Accurate and timely identification of these defects is essential for effective pest management and crop improvement. This review paper explores recent advancements in sugarcane leaf defect identification, focusing on technological progress and methodological innovations. The study covers traditional techniques, such as visual inspections and manual identification, and examines how modern approaches, including machine learning, computer vision, and remote sensing, have transformed the field. Recent progress in image processing technologies and the development of automated systems have greatly enhanced the accuracy and efficiency of defect detection. Despite these advancements, challenges remain, including variability in defect appearance, the need for large annotated datasets, and the integration of detection systems into practical agricultural practices. The review also discusses the impact of these technologies on improving disease management, optimizing yield, and supporting sustainable farming practices. By highlighting current trends and future directions, this paper aims to provide a comprehensive understanding of the state-of-the-art methods in sugarcane leaf defect identification and their implications for the agricultural industry.