Efficient Detection of Sugarcane Diseases through Intelligent Approaches: A Review
R. Manavalan *
Department of Computer Science, Arignar Anna Government Arts College, Villupuram – 605 602, Tamilnadu, India.
*Author to whom correspondence should be addressed.
Abstract
Agriculture is the most important sector that influences the country's economic growth, and is closely related to all quadrangle of the society. Sugarcane is India's most promising crop. It is grown as a main crop or as a cash crop. Low to medium-sized rural farmers harvest sugarcane for the manufacture of brown sugar to animal feeding. The sugarcane industry utilizes sugarcane compounds to manufacture sugar, bio-electricity, bio-ethanol and other chemical products. There is a need to increase the sugarcane yield to cope with the world’s growing population. The sugarcane production is severely affected by pests and various diseases. Hence, the farmers as well as nation severely suffer from economic losses. Therefore, the early diagnosis of various sugarcane diseases and pest’s controls techniques are necessary to increase the production. The identification of the sugarcane leaves diseases in naked eyes leads to inaccurate control measurements of pesticides. Hence, an automatic identification and early diagnosis of sugarcane diseases is necessary to increase the production and quality. Image processing techniques efficiently extracts feature from the sugarcane leaves and also identifies the types of diseases in early stage. This paper exhibits survey on different image processing technique and machine learning approaches used to extract and quick examination of sugarcane diagnosis. The issues behind the computational approaches for analyzing sugarcane diseases are also discussed with future directions.
Keywords: Plant diseases, sugarcane, classification, feature extraction, computational model