The use of co-occurrence patterns in single image based food portion estimation

© 2017 IEEE. Measuring accurate dietary intake is considered to be an open research problem in the nutrition and health fields. Food portions estimation is a challenging problem as food preparation and consumption process pose large variations on food shapes and appearances. We use geometric model b...

Full description

Bibliographic Details
Main Authors: Fang, S., Zhu, F., Boushey, Carol, Delp, E.
Format: Conference Paper
Published: 2018
Online Access:http://hdl.handle.net/20.500.11937/68941
_version_ 1848761927295041536
author Fang, S.
Zhu, F.
Boushey, Carol
Delp, E.
author_facet Fang, S.
Zhu, F.
Boushey, Carol
Delp, E.
author_sort Fang, S.
building Curtin Institutional Repository
collection Online Access
description © 2017 IEEE. Measuring accurate dietary intake is considered to be an open research problem in the nutrition and health fields. Food portions estimation is a challenging problem as food preparation and consumption process pose large variations on food shapes and appearances. We use geometric model based technique to estimate food portions and further improve estimation accuracy using co-occurrence patterns. We estimate the food portion co-occurrence patterns from food images we collected from dietary studies using the mobile Food Record (mFR) system we developed. Co-occurrence patterns is used as prior knowledge to refine portion estimation results. We show that the portion estimation accuracy has been improved when in-corporating the co-occurrence patterns as contextual information.
first_indexed 2025-11-14T10:39:27Z
format Conference Paper
id curtin-20.500.11937-68941
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:39:27Z
publishDate 2018
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-689412018-06-29T12:35:48Z The use of co-occurrence patterns in single image based food portion estimation Fang, S. Zhu, F. Boushey, Carol Delp, E. © 2017 IEEE. Measuring accurate dietary intake is considered to be an open research problem in the nutrition and health fields. Food portions estimation is a challenging problem as food preparation and consumption process pose large variations on food shapes and appearances. We use geometric model based technique to estimate food portions and further improve estimation accuracy using co-occurrence patterns. We estimate the food portion co-occurrence patterns from food images we collected from dietary studies using the mobile Food Record (mFR) system we developed. Co-occurrence patterns is used as prior knowledge to refine portion estimation results. We show that the portion estimation accuracy has been improved when in-corporating the co-occurrence patterns as contextual information. 2018 Conference Paper http://hdl.handle.net/20.500.11937/68941 10.1109/GlobalSIP.2017.8308685 restricted
spellingShingle Fang, S.
Zhu, F.
Boushey, Carol
Delp, E.
The use of co-occurrence patterns in single image based food portion estimation
title The use of co-occurrence patterns in single image based food portion estimation
title_full The use of co-occurrence patterns in single image based food portion estimation
title_fullStr The use of co-occurrence patterns in single image based food portion estimation
title_full_unstemmed The use of co-occurrence patterns in single image based food portion estimation
title_short The use of co-occurrence patterns in single image based food portion estimation
title_sort use of co-occurrence patterns in single image based food portion estimation
url http://hdl.handle.net/20.500.11937/68941