Abstract: This paper is an attempt to automatically grade the disease on the Pomegranate plant leaves. This innovative technique would be a boon to many and would have a lot of advantages over the traditional method of grading. There has been a sea change in the mindset and the effort put down by the agricultural industry by adapting to the current trends & technologies. One such example is the use of Information and Communication Technology (ICT) in agriculture which eventually contributes to Precision Agriculture. Presently, plant pathologists follow a tedious technique that mainly relies on naked eye prediction and a disease scoring scale to grade the disease. Manual grading is not only time consuming but also does not give precise results. Hence the current paper proposes an image processing methodology to deal with one of the main issues of plant pathology i.e. disease grading. The results are proved to be accurate and satisfactory in contrast to manual grading and hopefully take a strong leap forward in establishing itself in the market as one of the most efficient and effective process. The proposed system is also an efficient module that identifies the Bacterial Blight disease on pomegranate plant. At first, the captured images are processed for enhancement. Then image segmentation is carried out to get target regions (disease spots) on the leaves and fruits. Later, if the diseased spot on leaf is bordered by yellow margin then it is said that leaf is infected by bacterial blight otherwise not. Similarly when black spots are targeted on fruits, they are checked for whether a crack is passing through these spots. If cracks are passing through the spots then the disease identified would be Bacterial blight. Based on these two characteristics bacterial blight on pomegranate can be appropriately identified.

Keywords: Percent Infection, Bacterial Blight, K-means clustering, Morphology, colour image segmentation, Precision agriculture.