Machine Learning and SIFT Approach for Indonesian Food Image Recognition

Currently, image become one of the most popular research area, computer learn to recognize many kinds of object based on image. This research are developed since it becomes common habit to take a picture in any activities, for instances before having a meal. Capturing image of meal allows to extract information which contain in food for health reference. The challenge in food recognition that these objects have various shape and appearances, especially Indonesian food, which may have different character for same type of food based on origin of foods. This research proposes a technique in food recognition, especially Indonesian food, using SIFT and machine learning techniques. K-Dimensional Tree (K-D Tree) and Backpropagation Neural network (BPNN) are chosen as machine learning techniques to recognize three types of Indonesian food namely Bakso, Ayam bakar and Sate. Experimental results shows BPNN has higher accuracy compare to K-D Tree which is 51% and 44% for BPNN and K-D Tree respectively.