Detection of diseases on Cotton Leaves in Rural India Using CBIR

Abstract: The main source for the disease is the leaf of the cotton plant. About 80 to 90 % of disease on the cotton plant is on its leaves. So for that our study of interest is the leaf of the cotton tree rather than whole cotton plant the cotton leaf is mainly suffered from diseases like fungus, foliar leaf spot of cotton, Alternaria leaf spot of cotton. The machine vision system now a day is normally consists of computer, digital camera and application software. We wanted to propose this project is to produce a working system that is capable of image retrieval through the use of content analysis and associated metadata in the form of supplied cotton leaf images. Existing system based on fuzzy feature selection approach using fuzzy curves (FC) and surface (FS). The reported accuracy in the literature is around 60%. We are using two approaches to image retrieval: Text-Based approach and Content-Based approach. Our approach is more effective and raises the accuracy rate to 80%.CBIR systems search collection of images based on features that can be extracted from the image Files themselves without manual descriptive. Our propose system will have android application for farmer which will allow farmer to take snapshot of cotton leaf and show the diagnosis.

Keywords: Fuzzy curves(FC),Fuzzy Surface(FS),Contain Based Image Retrieval(CBIR),Colour Co-occurrence Matrix(CCM),Gray Level Co-occurrence Matrix(GLCM),Histogram(HSV).