TYPE I and TYPE II Diabetic Food Recognition System using BAYESIAN, SVM, PARZEN WINDOW, ANN Classifiers

The inability to control the disorder in diabetic people, computer-aided habitual food detection system has wedged more consideration now days. The food image processing is the most gifted tool is used for food identification. Scale Invariant Feature Transform (SIFT) algorithm is used to extract the color key points from food image. It is used for building visual dictionary which based on color using k-means clustering algorithm. Features can be grouped into two classes, specifically class I and II. By BAYESIAN, PARZEN WINDOW, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) kernels such as are used for identifying the input food image belong to eatable category or not eatable category. GLCM parameters are to evaluate different calories from food image for diabetic patients. As a final point compare the recognition accuracy value for various classifiers. The recognition accuracy for various classifiers is used to show the likelihood of the approach in a very huge food image dataset. This project is about consciousness on food particularly for diabetic patients.