Image Processing Techniques for Detecting and Classification of Plant Disease

Abstract

Agriculture is the main contributor to Tanzania Economy. Apart from climate change, disease acts as one of contributing factors which results in the poor production of the most important staple foods like maize and cassava. This leads to economic loss and food insecurity in the area. Preventive action is needed for early detection of the diseases. Image processing techniques to detect disease on plant leaves can be a promising solution to the farmer. The current way of detecting disease using naked eyes done by an expert is a time-consuming and cumbersome task to implement in a large farm. This paper presents a survey of current studies in the area of image processing, by checking techniques used to detect disease on plants leaves or fruits and machine learning model used to classify the disease. The main aim of the paper is to show the current state of the art and clarify step taken during the image processing stage and check merit and demerit of each technique used also the performance of the machine learning model used to classify the disease. This review paper will be of important to other researchers working in the area of image processing for detecting and classification of plant -- leaves/fruit diseases to know the current state of the art in the field.