Efficient superpixel based segmentation for food image analysis

In this paper, we propose a segmentation method based on normalized cut and superpixels. The method relies on color and texture cues for fast computation and efficient use of memory. The method is used for food image segmentation as part of a mobile food record system we have developed for dietary a...

Full description

Bibliographic Details
Main Authors: Wang, Y., Liu, C., Zhu, F., Boushey, Carol, Delp, E.
Format: Conference Paper
Published: 2016
Online Access:http://hdl.handle.net/20.500.11937/51133
_version_ 1848758623587532800
author Wang, Y.
Liu, C.
Zhu, F.
Boushey, Carol
Delp, E.
author_facet Wang, Y.
Liu, C.
Zhu, F.
Boushey, Carol
Delp, E.
author_sort Wang, Y.
building Curtin Institutional Repository
collection Online Access
description In this paper, we propose a segmentation method based on normalized cut and superpixels. The method relies on color and texture cues for fast computation and efficient use of memory. The method is used for food image segmentation as part of a mobile food record system we have developed for dietary assessment and management. The accurate estimate of nutrients relies on correctly labelled food items and sufficiently well-segmented regions. Our method achieves competitive results using the Berkeley Segmentation Dataset and outperforms some of the most popular techniques in a food image dataset.
first_indexed 2025-11-14T09:46:56Z
format Conference Paper
id curtin-20.500.11937-51133
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-20.500.11937-511332017-09-13T15:50:27Z Efficient superpixel based segmentation for food image analysis Wang, Y. Liu, C. Zhu, F. Boushey, Carol Delp, E. In this paper, we propose a segmentation method based on normalized cut and superpixels. The method relies on color and texture cues for fast computation and efficient use of memory. The method is used for food image segmentation as part of a mobile food record system we have developed for dietary assessment and management. The accurate estimate of nutrients relies on correctly labelled food items and sufficiently well-segmented regions. Our method achieves competitive results using the Berkeley Segmentation Dataset and outperforms some of the most popular techniques in a food image dataset. 2016 Conference Paper http://hdl.handle.net/20.500.11937/51133 10.1109/ICIP.2016.7532818 restricted
spellingShingle Wang, Y.
Liu, C.
Zhu, F.
Boushey, Carol
Delp, E.
Efficient superpixel based segmentation for food image analysis
title Efficient superpixel based segmentation for food image analysis
title_full Efficient superpixel based segmentation for food image analysis
title_fullStr Efficient superpixel based segmentation for food image analysis
title_full_unstemmed Efficient superpixel based segmentation for food image analysis
title_short Efficient superpixel based segmentation for food image analysis
title_sort efficient superpixel based segmentation for food image analysis
url http://hdl.handle.net/20.500.11937/51133