Design and Development of Classifier for Mango Leaf Disease Detection

Abstract

In recent times, the images and videos have emerged as one of the most important information newlinesources depicting the real time scenarios. Digital images nowadays serve as input for many newlineapplications and replacing the manual methods due to their capabilities of 3D scene representation newlinein 2D plane. The capabilities of digital images along with utilization of Machine learning newlinemethodologies are showing promising accuracies in many applications of prediction and pattern newlinerecognition. One of the application fields pertains to detection of diseases occurring in the plants, newlinewhich are destroying the wide spread fields. Traditionally the disease detection process was done newlineby a domain expert using manual examination and laboratory tests. This is a tedious and timeconsuming process and does not suffice the accuracy levels. This creates a room for the research in newlinedeveloping automation-based methods where the images captured through sensors and cameras will newlinebe used for detection of disease and control its spreading. The digital images captured from the newlinefield s forms the dataset which trains the machine learning models to predict the nature of the newlinedisease. The accuracy of these modelsis greatly affected by the amount of noise and ailments present newlinein the input images, appropriate segmentation methodology, feature vector development and the newlinechoice of machine learning algorithm. To ensure the high rated performance of the designed system newlinethe research is moving in a direction to fine tune each stage separately considering their newlinedependencies on subsequent stages. Therefore, the most optimum solution can be obtained by newlineconsidering the image processing methodologies for improving the quality of image and then newlineapplying statistical methods for feature extraction and selection. The training vector thus developed newlinecan present the relationship between the feature values and the target class. newline newline