Show simple item record

dc.contributor.authorHe, Y.
dc.contributor.authorXu, C.
dc.contributor.authorKhanna, N.
dc.contributor.authorBoushey, Carol
dc.contributor.authorDelp, E.
dc.date.accessioned2017-03-17T08:28:50Z
dc.date.available2017-03-17T08:28:50Z
dc.date.created2017-02-19T19:31:47Z
dc.date.issued2014
dc.identifier.citationHe, Y. and Xu, C. and Khanna, N. and Boushey, C. and Delp, E. 2014. Analysis of food images: Features and classification, in Proceedings of the International Conference on Image Processing (ICIP), Oct 27-30 2014, pp. 2744-2748. Paris, France: IEEE.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/50858
dc.identifier.doi10.1109/ICIP.2014.7025555
dc.description.abstract

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.

dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.titleAnalysis of food images: Features and classification
dc.typeConference Paper
dcterms.source.startPage2744
dcterms.source.endPage2748
dcterms.source.title2014 IEEE International Conference on Image Processing, ICIP 2014
dcterms.source.series2014 IEEE International Conference on Image Processing, ICIP 2014
dcterms.source.isbn9781479957514
curtin.departmentSchool of Public Health
curtin.accessStatusFulltext not available


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record