Detection of critical diseases in rice crop Using GLCM Texture Feature Algorithm

The Research work focus on rice disease detection using image analysis algorithm. The images are captured using the camera with the resolution (512X512) and processed using Gray Level Co-occurrence Matrix Texture Feature Algorithm can detect the diseases in the crop. The design of algorithm is based on dividing the image into two parts; one is patchareas other the grass areas. Patch denotes the diseases affected portion and grass shows the unaffected portion. The objective of the research is to detect the diseases in early stage and stop spreading to the other plants. As per the report of International Rice Research Institute(IRRI), 37 %crops are wasted due to diseases alone. To find the disease in the plants, we used theabove mentioned algorithms. 84 samples of leaf affectedimages (42 for training and 42 for testing purposes) were taken for consideration, and got the accuracy about 100%. Run time for the each leaf sample is also noted. Maximum run time has not exceeded more than 2 minutes, which shows that the performance of the algorithm is good in terms of detection time.