Day by Day, the population keeps on increasing across the world. In the upcoming years providing food for people around the globe is the major challenge. Among all crops, Rice is the important crop for providing food for more than half of the population around the world. The major challenge in the cultivation of Rice crops is identifying the diseases early. But recognizing illness with the naked eye is sometimes tricky as a result of the productivity affecting. This study focuses on the early detection of Rice leaf disease to improve the overall productivity by more than 20 percent. This paper proposed a Convolution Neural Network (CNN) and deep learning approach to detect and classify diseases like Stem borer, Sheath Blight Rot Brown Spot, False Smut. The major challenge in identifying the leaf disease is that the condition may affect any leaf with different sizes. So a dataset of 1045 images was gathered to train the KNN model. Initially, KNN classifies the leaf with disease and without the disease. In the second phase, the Classification of the Disease will take place by using CNN. Using this approach, we got 95% accuracy for finding healthy leaf and 90% accuracy (highest among all diseases) for Sheath Blight.
Automated Classification of rice leaf disease using Deep Learning Approach
2021-12-02
567162 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Automated Rice Phenology Stage Mapping Using UAV Images and Deep Learning
DOAJ | 2023
|Deep Learning Based Approach for Gender Classification
IEEE | 2018
|