Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images.
Several lines of evidence suggest that facial cues of adiposity may be important for human social interaction. However, tests for quantifiable cues of body mass index (BMI) in the face have examined only a small number of facial proportions and these proportions were found to have relatively low pre...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2015-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0140347&type=printable |
| _version_ | 1826584250547175424 |
|---|---|
| author | Karin Wolffhechel Amanda C Hahn Hanne Jarmer Claire I Fisher Benedict C Jones Lisa M DeBruine |
| author_facet | Karin Wolffhechel Amanda C Hahn Hanne Jarmer Claire I Fisher Benedict C Jones Lisa M DeBruine |
| author_sort | Karin Wolffhechel |
| collection | DOAJ |
| description | Several lines of evidence suggest that facial cues of adiposity may be important for human social interaction. However, tests for quantifiable cues of body mass index (BMI) in the face have examined only a small number of facial proportions and these proportions were found to have relatively low predictive power. Here we employed a data-driven approach in which statistical models were built using principal components (PCs) derived from objectively defined shape and color characteristics in face images. The predictive power of these models was then compared with models based on previously studied facial proportions (perimeter-to-area ratio, width-to-height ratio, and cheek-to-jaw width). Models based on 2D shape-only PCs, color-only PCs, and 2D shape and color PCs combined each performed significantly and substantially better than models based on one or more of the previously studied facial proportions. A non-linear PC model considering both 2D shape and color PCs was the best predictor of BMI. These results highlight the utility of a "bottom-up", data-driven approach for assessing BMI from face images. |
| first_indexed | 2024-12-21T18:44:05Z |
| format | Article |
| id | doaj.art-6c312aee2d3140fd8779b59bd21fa014 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2025-03-14T15:34:46Z |
| publishDate | 2015-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-6c312aee2d3140fd8779b59bd21fa0142025-02-25T05:33:47ZengPublic Library of Science (PLoS)PLoS ONE1932-62032015-01-011010e014034710.1371/journal.pone.0140347Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images.Karin WolffhechelAmanda C HahnHanne JarmerClaire I FisherBenedict C JonesLisa M DeBruineSeveral lines of evidence suggest that facial cues of adiposity may be important for human social interaction. However, tests for quantifiable cues of body mass index (BMI) in the face have examined only a small number of facial proportions and these proportions were found to have relatively low predictive power. Here we employed a data-driven approach in which statistical models were built using principal components (PCs) derived from objectively defined shape and color characteristics in face images. The predictive power of these models was then compared with models based on previously studied facial proportions (perimeter-to-area ratio, width-to-height ratio, and cheek-to-jaw width). Models based on 2D shape-only PCs, color-only PCs, and 2D shape and color PCs combined each performed significantly and substantially better than models based on one or more of the previously studied facial proportions. A non-linear PC model considering both 2D shape and color PCs was the best predictor of BMI. These results highlight the utility of a "bottom-up", data-driven approach for assessing BMI from face images.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0140347&type=printable |
| spellingShingle | Karin Wolffhechel Amanda C Hahn Hanne Jarmer Claire I Fisher Benedict C Jones Lisa M DeBruine Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images. PLoS ONE |
| title | Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images. |
| title_full | Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images. |
| title_fullStr | Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images. |
| title_full_unstemmed | Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images. |
| title_short | Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images. |
| title_sort | testing the utility of a data driven approach for assessing bmi from face images |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0140347&type=printable |
| work_keys_str_mv | AT karinwolffhechel testingtheutilityofadatadrivenapproachforassessingbmifromfaceimages AT amandachahn testingtheutilityofadatadrivenapproachforassessingbmifromfaceimages AT hannejarmer testingtheutilityofadatadrivenapproachforassessingbmifromfaceimages AT claireifisher testingtheutilityofadatadrivenapproachforassessingbmifromfaceimages AT benedictcjones testingtheutilityofadatadrivenapproachforassessingbmifromfaceimages AT lisamdebruine testingtheutilityofadatadrivenapproachforassessingbmifromfaceimages |