Image-based food volume estimation

In this paper, we propose an extension to our previous work on food portion size estimation using a single image and a multi-view volume estimation method. The single-view technique estimates food volume by using prior information (segmentation and food labels) generated from food identification met...

Full description

Bibliographic Details
Main Authors: Xu, C., He, Y., Parra, A., Delp, E., Khanna, N., Boushey, Carol
Format: Conference Paper
Published: Association for Computing Machinery 2013
Online Access:http://hdl.handle.net/20.500.11937/50009
_version_ 1848758372067704832
author Xu, C.
He, Y.
Parra, A.
Delp, E.
Khanna, N.
Boushey, Carol
author_facet Xu, C.
He, Y.
Parra, A.
Delp, E.
Khanna, N.
Boushey, Carol
author_sort Xu, C.
building Curtin Institutional Repository
collection Online Access
description In this paper, we propose an extension to our previous work on food portion size estimation using a single image and a multi-view volume estimation method. The single-view technique estimates food volume by using prior information (segmentation and food labels) generated from food identification methods we described earlier. For multi-view volume estimation, we use "Shape from Silhouettes" to estimate the food portion size. The experimental results of our volume estimation methods demonstrate our results with respect to accuracy and reliability. © Copyright 2013 ACM.
first_indexed 2025-11-14T09:42:56Z
format Conference Paper
id curtin-20.500.11937-50009
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:42:56Z
publishDate 2013
publisher Association for Computing Machinery
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-500092018-03-29T09:07:08Z Image-based food volume estimation Xu, C. He, Y. Parra, A. Delp, E. Khanna, N. Boushey, Carol In this paper, we propose an extension to our previous work on food portion size estimation using a single image and a multi-view volume estimation method. The single-view technique estimates food volume by using prior information (segmentation and food labels) generated from food identification methods we described earlier. For multi-view volume estimation, we use "Shape from Silhouettes" to estimate the food portion size. The experimental results of our volume estimation methods demonstrate our results with respect to accuracy and reliability. © Copyright 2013 ACM. 2013 Conference Paper http://hdl.handle.net/20.500.11937/50009 10.1145/2506023.2506037 Association for Computing Machinery restricted
spellingShingle Xu, C.
He, Y.
Parra, A.
Delp, E.
Khanna, N.
Boushey, Carol
Image-based food volume estimation
title Image-based food volume estimation
title_full Image-based food volume estimation
title_fullStr Image-based food volume estimation
title_full_unstemmed Image-based food volume estimation
title_short Image-based food volume estimation
title_sort image-based food volume estimation
url http://hdl.handle.net/20.500.11937/50009