A Comprehensive Review: Sugarcane Disease Detection Using Intelligent Approaches

Agriculture is the most important sector in terms of influencing the economic growth of country, and it is intertwined with all four quadrants of society. India's most promising and widely cultivated crop is sugarcane. It can be planted as a cash crop or a major crop. Sugarcane is harvested by small to medium-sized peasant for the production of brown sugar used for feeding animals. Sugarcane complexes are used in the sugarcane business to make white sugar, bio-electricity, bio-ethanol, and many more organic products. To keep up with the world's rising population, sugarcane yields must be increased. Pests and illnesses have a significant impact on sugarcane productivity. As a result, both farmers and the country incur significant economic losses. As a result, early detection of numerous sugarcane diseases and pest management strategies are required to boost productivity. The inability to identify sugarcane leaf diseases with the bare eye leads to flawed insecticide regulator measurements. To boost productivity and quality, an automatic detection and early diagnosis of sugarcane illnesses is required. Algorithms used in processing of images extract features from sugarcane leaves rapidly and identify ailment types at an initial stage. This study presents a survey of several image processing techniques and deep learning approaches for sugarcane diagnosis extraction and rapid assessment. The challenges that underpin computational approaches for assessing sugarcane infections are also highlighted, as well as possible future possibilities.