Calorie Estimation From Pictures of Food: Crowdsourcing Study
Name:
6934c126-49a7-480c-960c-bb73ca ...
Size:
2.148Mb
Format:
PDF
Description:
Final Published version
Affiliation
Univ Arizona, Dept LinguistUniv Arizona, Dept Comp Sci
Univ Arizona, Dept Nutr Sci
Issue Date
2018-11-05Metadata
Show full item recordPublisher
JMIR PUBLICATIONS, INCCitation
Zhou J, Bell D, Nusrat S, Hingle M, Surdeanu M, Kobourov S Calorie Estimation From Pictures of Food: Crowdsourcing Study Interact J Med Res 2018;7(2):e17 URL: https://www.i-jmr.org/2018/2/e17 DOI: 10.2196/ijmr.9359 PMID: 30401671 PMCID: 6246963Rights
©Jun Zhou, Dane Bell, Sabrina Nusrat, Melanie Hingle, Mihai Surdeanu, Stephen Kobourov. Originally published in the Interactive Journal of Medical Research (http://www.i-jmr.org/), 05.11.2018. This is an open-access article distributed under the terms of the Creative Commons Attribution License.Collection Information
This item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.Abstract
A total of 2028 respondents agreed to participate in the study (males: 770/2028, 37.97%, mean body mass index: 27.5 kg/m2). Average accuracy was 5 out of 20 correct guesses, where "correct" was defined as a number within 20% of the ground truth. Even a small crowd of 10 individuals achieved an accuracy of 7, exceeding the average individual and expert annotator's accuracy of 5. Women were more accurate than men (P<.001), and younger people were more accurate than older people (P<.001). The calorie content of energy-dense foods was overestimated (P=.02). Participants performed worse when images contained reference objects, such as credit cards, for scale (P=.01).Note
Open access journalISSN
1929-073XPubMed ID
30401671Version
Final published versionAdditional Links
https://www.i-jmr.org/2018/2/e17/Scopus Count
Collections
Except where otherwise noted, this item's license is described as ©Jun Zhou, Dane Bell, Sabrina Nusrat, Melanie Hingle, Mihai Surdeanu, Stephen Kobourov. Originally published in the Interactive Journal of Medical Research (http://www.i-jmr.org/), 05.11.2018. This is an open-access article distributed under the terms of the Creative Commons Attribution License.