Rice Leaf Disease Identification Using Minimum Distance Vector Classifier

Abstract

Agriculture is now the most important strategy compared to what it was a few years ago, when plants were employed to feed humans and flora and animals. Plants are being employed to generate electricity and other forms of power in order to improve the living conditions of social beings. As a result, proper plant care is essential in order to obtain the greatest benefit. Cutting plant leaves illnesses are the key area that requires special attention. A number of illnesses harm the leaves, potentially wreaking havoc on several economic and social aspects. It may also result in significant environmental damage. However, the current inquiry lacks the ability to accurately and quickly identify illnesses in order to provide precision agriculture. Investigate various leaf pathogens utilising image processing detection and classification techniques in the suggested system. Initially, digital photographs were used to collect diverse paddy leaves. After that, the RGB model was converted to the Grayscale model, which was then used to resize to improve the quality of an image and image segmentation and then doing classification based on algorithm.To address this issue, this paper examined certain automated strategies that aid in the detection of leaf disease at an early stage, reducing the amount of monitoring effort required in vast farms of crops, as well as the need for a large team of experts and constant plant monitoring. This study looked at many forms of image segmentation and minimum distance vector classifier classification algorithms that can be used to detect a plant leaf disease automatically with the better accuracy.