Analysis of food images: Features and classification

In this paper we investigate features and their combinations for food image analysis and a classification approach based on k-nearest neighbors and vocabulary trees. The system is evaluated on a food image dataset consisting of 1453 images of eating occasions in 42 food categories which were acquire...

Full description

Bibliographic Details
Main Authors: He, Y., Xu, C., Khanna, N., Boushey, Carol, Delp, E.
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2014
Online Access:http://hdl.handle.net/20.500.11937/50858
_version_ 1848758553359155200
author He, Y.
Xu, C.
Khanna, N.
Boushey, Carol
Delp, E.
author_facet He, Y.
Xu, C.
Khanna, N.
Boushey, Carol
Delp, E.
author_sort He, Y.
building Curtin Institutional Repository
collection Online Access
description In this paper we investigate features and their combinations for food image analysis and a classification approach based on k-nearest neighbors and vocabulary trees. The system is evaluated on a food image dataset consisting of 1453 images of eating occasions in 42 food categories which were acquired by 45 participants in natural eating conditions. The same image dataset is used to test the classification system proposed in the previously reported work [1]. Experimental results indicate that using our combination of features and vocabulary trees for classification improves the food classification performance about 22% for the Top 1 classification accuracy and 10% for the Top 4 classification accuracy.
first_indexed 2025-11-14T09:45:49Z
format Conference Paper
id curtin-20.500.11937-50858
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:45:49Z
publishDate 2014
publisher Institute of Electrical and Electronics Engineers Inc.
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-508582018-03-29T09:09:27Z Analysis of food images: Features and classification He, Y. Xu, C. Khanna, N. Boushey, Carol Delp, E. In this paper we investigate features and their combinations for food image analysis and a classification approach based on k-nearest neighbors and vocabulary trees. The system is evaluated on a food image dataset consisting of 1453 images of eating occasions in 42 food categories which were acquired by 45 participants in natural eating conditions. The same image dataset is used to test the classification system proposed in the previously reported work [1]. Experimental results indicate that using our combination of features and vocabulary trees for classification improves the food classification performance about 22% for the Top 1 classification accuracy and 10% for the Top 4 classification accuracy. 2014 Conference Paper http://hdl.handle.net/20.500.11937/50858 10.1109/ICIP.2014.7025555 Institute of Electrical and Electronics Engineers Inc. restricted
spellingShingle He, Y.
Xu, C.
Khanna, N.
Boushey, Carol
Delp, E.
Analysis of food images: Features and classification
title Analysis of food images: Features and classification
title_full Analysis of food images: Features and classification
title_fullStr Analysis of food images: Features and classification
title_full_unstemmed Analysis of food images: Features and classification
title_short Analysis of food images: Features and classification
title_sort analysis of food images: features and classification
url http://hdl.handle.net/20.500.11937/50858