Sugarcane Disease Identification by using Machine Learning

Abstract

Agriculture is the most important sector that influences the country’s economic growth and is closely related to all quadrangles of society. Sugarcane is Pakistan’s most promising crop. It is grown as a cash crop in Pakistan, Low to medium-sized rural farmers harvest sugarcane for the manufacture of brown sugar for animal feeding. Sugarcane diseases have been a significant aspect of decreased crop production over the years. different types of the disease occur predominantly in some Asian countries and are a devastating global threat to sugarcane industries Ultimately they cause the farmers a decline in the profit that they earn from their annual harvest. This problematic scenario can be avoided if the fields are monitored closely right from the beginning, that is planting stage to the harvesting stage. But this method is only applicable if the crops have been planted on a small-scale farm. The work done in this Project will automate this manual process of identifying the disease and inculcate the methods used by humans to distinguish between diseased and healthy plants. The proposed system in this project is going to assist the farmers in looking out for different kinds of Sugarcane leaf diseases in their fields before things get out of hand. The current work has taken the sugarcane plants as a test data set and then by using Image Processing and computer vision techniques for the detection of diseases in sugarcane plants by observing the leaves. A few major diseases in sugarcane plants like red rot, mosaic, and leaf scald have been studied and a detection algorithm for the same has been implemented in this Project work it will detect diseases and return its result which will be forwarded to the user via the mobile application. If the result comes out positive the farmer can take precautionary measures before the disease spreads in the whole field. We evaluate the performance of our method using a dataset of sugarcane disease images and demonstrate its effectiveness in accurately identifying and diagnosing various sugarcane diseases. Our approach has the potential to significantly improve the efficiency and effectiveness of disease management in sugarcane production.