Disease recognition in Mango crop using modified rotational kernel transform features

Soft computing in the field of agriculture science is being employed with computer vision techniques in order to detect the diseases in crops to increase the overall yield. A Modified Rotation Kernel Transformation(MRKT) based directional feature extraction scheme is presents to resolve the issues occurring due to shape, color or other deceptive features during plant disease recognition. The MRKT based scheme is used to calculate the directional features and histograms for plant parts like leaf and fruit of Mango crop. These histograms and the directional feature set with use of artificial neural network lead to a better recognition technique of Anthracnose disease which occurs in form of black spots on fruits and leaves of mango plant. The results obtained using proposed MRKT directional feature set have shows the better results with accuracy up to 98%.