Simultaneous Food Localization and Recognition
This enables automatic nutrition diaries for people concerned about their diet, though it appears incremental as it adapts object localization techniques to a specific domain.
The paper tackles the problem of automatically tracking food consumption by proposing the first method for simultaneous food localization and recognition, achieving high precision and reasonable recall with few bounding boxes in both conventional and egocentric images.
The development of automatic nutrition diaries, which would allow to keep track objectively of everything we eat, could enable a whole new world of possibilities for people concerned about their nutrition patterns. With this purpose, in this paper we propose the first method for simultaneous food localization and recognition. Our method is based on two main steps, which consist in, first, produce a food activation map on the input image (i.e. heat map of probabilities) for generating bounding boxes proposals and, second, recognize each of the food types or food-related objects present in each bounding box. We demonstrate that our proposal, compared to the most similar problem nowadays - object localization, is able to obtain high precision and reasonable recall levels with only a few bounding boxes. Furthermore, we show that it is applicable to both conventional and egocentric images.