Sparse model in hierarchic spatial structure for food image recognition

Recent year, with the increasing of unhealthy diets which will threaten people's life due to the various resulted risks such as heart stroke, liver trouble and so on, the remain for healthy life has attracted much attention and then how to manage the dietary life is becoming more and more important. In this research, we aim to construct a auto-recognition system of food images and keep the daily food-log records which will contribute to manage dietary life. With the easily available food images taken by mobile phone, it prospects to give the insight about the daily dietary of users with our constructed food recognition system. In order to achieve the acceptable recognition performance of the food images, we propose to apply a sparse model for coding a local descriptor extracted from the food images. Sparse coding: an extension of vector quantization for local descriptors, which is popularly used in Bag-of-Features (BoF) for image representation in generic object recognition, can represent the local descriptors more efficient, and then abtain more discriminant feature for food image representation. Moreover, in order to introduce spatial information, a hierarchic spatial structure is explored to extract the feature based sparse model. Experiments validate that the proposed strategy can greatly improve the recognition rates compared with the conventional BOF model on two databases: our constructed RFID and the public PFID.