Disease Identification and Grading of Pomegranate Leaves Using Image Processing and Fuzzy Logic

Plant diseases cause major losses to several agricultural and horticultural crops around the World. Therefore, methods for proper diagnosis of diseases found in any parts of the plant body play a crucial role in disease management. In the past few decades, many methods and techniques of image processing and soft computing are applied on a number of plants to diagnose and treat variety of plant diseases. Hence, the present work is aimed to develop an automated system that results in three major outcomes for a leaf image. They are disease identification, disease grading and treatment advisory. The methodology begins with capturing of samples of healthy and diseased leaf images of Pomegranate plant. All the images are made to undergo pre-processing steps and different features are extracted and stored in the database. Analysis is done on the extracted features to determine those features that constitute a disease in the leaf. Later, a query image is taken and is tested to determine whether that image is healthy or diseased one. If the query image is found to be diseased, then the grade of the disease is determined. Finally, a treatment advisory module is built which ultimately helps agriculturists/farmers.