Single-View Food Portion Estimation Based on Geometric Models
In this paper we present a food portion estimation technique based on a single-view food image used for the estimation of the amount of energy (in kilocalories) consumed at a meal. Unlike previous methods we have developed, the new technique is capable of estimating food portion without manual tunin...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2016
|
| Online Access: | http://hdl.handle.net/20.500.11937/51132 |
| _version_ | 1848758623289737216 |
|---|---|
| author | Fang, S. Liu, C. Zhu, F. Delp, E. Boushey, Carol |
| author_facet | Fang, S. Liu, C. Zhu, F. Delp, E. Boushey, Carol |
| author_sort | Fang, S. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | In this paper we present a food portion estimation technique based on a single-view food image used for the estimation of the amount of energy (in kilocalories) consumed at a meal. Unlike previous methods we have developed, the new technique is capable of estimating food portion without manual tuning of parameters. Although single-view 3D scene reconstruction is in general an ill-posed problem, the use of geometric models such as the shape of a container can help to partially recover 3D parameters of food items in the scene. Based on the estimated 3D parameters of each food item and a reference object in the scene, the volume of each food item in the image can be determined. The weight of each food can then be estimated using the density of the food item. We were able to achieve an error of less than 6% for energy estimation of an image of a meal assuming accurate segmentation and food classification. |
| first_indexed | 2025-11-14T09:46:56Z |
| format | Conference Paper |
| id | curtin-20.500.11937-51132 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T09:46:56Z |
| publishDate | 2016 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-511322018-03-29T09:09:27Z Single-View Food Portion Estimation Based on Geometric Models Fang, S. Liu, C. Zhu, F. Delp, E. Boushey, Carol In this paper we present a food portion estimation technique based on a single-view food image used for the estimation of the amount of energy (in kilocalories) consumed at a meal. Unlike previous methods we have developed, the new technique is capable of estimating food portion without manual tuning of parameters. Although single-view 3D scene reconstruction is in general an ill-posed problem, the use of geometric models such as the shape of a container can help to partially recover 3D parameters of food items in the scene. Based on the estimated 3D parameters of each food item and a reference object in the scene, the volume of each food item in the image can be determined. The weight of each food can then be estimated using the density of the food item. We were able to achieve an error of less than 6% for energy estimation of an image of a meal assuming accurate segmentation and food classification. 2016 Conference Paper http://hdl.handle.net/20.500.11937/51132 10.1109/ISM.2015.67 restricted |
| spellingShingle | Fang, S. Liu, C. Zhu, F. Delp, E. Boushey, Carol Single-View Food Portion Estimation Based on Geometric Models |
| title | Single-View Food Portion Estimation Based on Geometric Models |
| title_full | Single-View Food Portion Estimation Based on Geometric Models |
| title_fullStr | Single-View Food Portion Estimation Based on Geometric Models |
| title_full_unstemmed | Single-View Food Portion Estimation Based on Geometric Models |
| title_short | Single-View Food Portion Estimation Based on Geometric Models |
| title_sort | single-view food portion estimation based on geometric models |
| url | http://hdl.handle.net/20.500.11937/51132 |