Key points are not available for this paper at this time.
Accurate assessment of nutrition information is an important part in the prevention and treatment of a multitude of diseases, but remains a challenging task. We present a novel mobile augmented reality application, which assists users in the nutrition assessment of their meals. Using the realtime camera image as a guide, the user overlays a 3D form of the food. Additionally the user selects the food type. The corresponding nutrition information is automatically computed. Thus accurate volume estimation is required for accurate nutrition information assessment. This work presents an evaluation of our mobile augmented reality approaches for portion estimation and offers a comparison to conventional portion estimation approaches. The comparison is performed on the basis of a user study (n=28). The quality of nutrition assessment is measured based on the error in energy units. In the results of the evaluation one of our mobile augmented reality approaches significantly outperforms all other methods. Additionally we present results on the efficiency and effectiveness of the approaches.
Stütz et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: