Enter your email address
Submit
Write your message
Volume 10, Issue 1 (Iranian Journal of Ergonomics 2022)
Iran J Ergon 2022, 10(1): 5-16 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Heidari M, Babapour Mofrad F, Shah-Hosseini H. Body Mass Index Classification based on Facial Features Using Machine Learning Algorithms for Utilizing in Telemedicine. Iran J Ergon 2022; 10 (1) :5-16
URL: http://journal.iehfs.ir/article-1-875-en.html
URL: http://journal.iehfs.ir/article-1-875-en.html
1- Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2- Department of Medical Radiation Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran , Farshid.mofrad@yahoo.com
2- Department of Medical Radiation Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran , Farshid.mofrad@yahoo.com
Abstract: (3675 Views)
Objectives: Given the benefits of controlling Body mass index (BMI) on the quality of life, BMI classification based on facial features can be used for developing telemedicine systems and eliminate the limitations of existing measuring tools especially for paralyzed people, that enable physicians to help people online when faced with situations like the COVID-19 pandemic.
Methods: In this study, new features and some previous-work features were extracted from face photos of white, black and Asian people, ages 18 to 81, with normal and overweight BMI. Faces were evaluated in three different steps. First, all faces were considered as one group. Second, they were divided into elliptical, round and square shape groups and third, they were separated based on gender. Then for each step, the performances of Random Forest (RF) and Support Vector Machine (SVM) were evaluated with all of the facial features and with selected features based on Pearson correlation coefficient. Matlab R2015b was used for implementation.
Results: The results revealed that features with higher correlation improved the accuracy of both algorithms. RF best performance using highly correlated features for 97 women and 92 men was in women and square-face groups (91.75% and 87.30% respectively), and SVM best performance was in women group (94.84%), square-face and round-face groups (84.12% and 84% respectively).
Conclusion: Accuracy of BMI classification based on facial features can be improved by categorizing faces into shapes and gender, and selecting appropriate features. The findings can be used for performance enhancement of telemedicine applications, especially for helping the differently-abled.
Methods: In this study, new features and some previous-work features were extracted from face photos of white, black and Asian people, ages 18 to 81, with normal and overweight BMI. Faces were evaluated in three different steps. First, all faces were considered as one group. Second, they were divided into elliptical, round and square shape groups and third, they were separated based on gender. Then for each step, the performances of Random Forest (RF) and Support Vector Machine (SVM) were evaluated with all of the facial features and with selected features based on Pearson correlation coefficient. Matlab R2015b was used for implementation.
Results: The results revealed that features with higher correlation improved the accuracy of both algorithms. RF best performance using highly correlated features for 97 women and 92 men was in women and square-face groups (91.75% and 87.30% respectively), and SVM best performance was in women group (94.84%), square-face and round-face groups (84.12% and 84% respectively).
Conclusion: Accuracy of BMI classification based on facial features can be improved by categorizing faces into shapes and gender, and selecting appropriate features. The findings can be used for performance enhancement of telemedicine applications, especially for helping the differently-abled.
Type of Study: Research |
Subject:
New Methods and Technologies in Ergonomic (Computational Intelligence)
Received: 2022/02/28 | Accepted: 2022/07/1 | ePublished: 2022/07/1
Received: 2022/02/28 | Accepted: 2022/07/1 | ePublished: 2022/07/1
References
1. Coetzee V, Perrett DI, Stephen ID. Facial adiposity: a cue to health? Perception. 2009; 38(11):1700-11. [DOI] [PubMed]
2. Coetzee V, Chen J, Perrett DI, Stephen ID. Deciphering faces: Quantifiable visual cues to weight. Perception. 2010; 39(1):51-61. [DOI] [PubMed]
3. Pham DD, Do JH, Ku B, Lee HJ, Kim H, Kim JY. Body mass index and facial cues in Sasang typology for young and elderly persons. Evid Based Complement Alternat Med. 2011; 2011:749209. [DOI] [PubMed]
4. Lee BJ, Jang JS, Kim JY. Prediction of body mass index from facial features of females and males. International Journal of Bio-Science and Bio-Technology. 2012;4(3):45-62.
5. Wen L, Guo G. A computational approach to body mass index prediction from face images. Image and Vision Computing. 2013; 31(5):392-400. [DOI]
6. Tai CH, Lin DT. A Framework for Healthcare Everywhere: BMI Prediction Using Kinect and Data Mining Techniques on Mobiles. In Mobile Data Management (MDM), 2015 16th IEEE International Conference on 2015 Jun 15 (Vol. 2, pp. 126-129). IEEE. [DOI]
7. Jiang M, Shang Y, Guo G. On visual BMI analysis from facial images. Image and Vision Computing. 2019;89:183-96. [DOI]
8. Jiang M, Guo G, Mu G. Visual BMI estimation from face images using a label distribution based method. Computer Vision and Image Understanding. 2020;197-198:102985. [DOI]
9. Carré JM, McCormick CM, Mondloch CJ. Facial structure is a reliable cue of aggressive behavior. Psychological Science. 2009;20(10):1194-8. [DOI] [PubMed]
10. Hehman E, Leitner JB, Freeman JB. The face–time continuum: Lifespan changes in facial width-to-height ratio impact aging-associated perceptions. Pers Soc Psychol Bull. 2014;40(12):1624-36. [DOI] [PubMed]
11. Wilson JP, Rule NO. Facial trustworthiness predicts extreme criminal-sentencing outcomes. Psychol Sci. 2015;26(8):1325-31. [DOI] [PubMed]
12. Tjepkema M. Adult obesity. Health Reports (statistics Canada, Catalogue 82-003), 2006;17(3):9-25.
13. Somerville LA, List RP, Compton MH, Bruschwein HM, Jennings D, Jones MK, et al. Real-world outcomes in cystic fibrosis telemedicine clinical care in a time of a global pandemic. Chest. 2022;161(5):1167-79. [DOI] [PubMed]
14. https://www.3d.sk/.2020.
15. Bansode NK, Sinha PK. Face shape classification based on region similarity, correlation and fractal dimensions. IJCSI. 2016;13(1):24-31. [DOI]
16. Sagonas C, Antonakos E, Tzimiropoulos G, Zafeiriou S, Pantic M. 300 faces in-the-wild challenge: Database and results. Image and Vision Computing. 2016;47:3-18. [DOI]
17. Jahan A, Edwards KL. A state-of-the-art survey on the influence of normalization techniques in ranking: Improving the materials selection process in engineering design. Materials and Design. 2015;65:335-42. [DOI]
18. Fernández-Blanco E, Aguiar-Pulido V, Munteanu CR, Dorado J. Random Forest classification based on star graph topological indices for antioxidant proteins. J Theor Biol. 2013;317:331-7. [DOI] [PubMed]
19. Zhu X, Du X, Kerich M, Lohoff FW, Momenan R. Random forest based classification of alcohol dependence patients and healthy controls using resting state MRI. Neurosci Lett. 2018;676:27-33. [DOI] [PubMed]
20. Zhao H, Chen X, Nguyen T, Huang JZ, Williams G, Chen H. Stratified over-sampling bagging method for random forests on imbalanced data. InPacific-Asia Workshop on Intelligence and Security Informatics 2016 Apr 19. Springer, Cham. pp. 63-72.
21. Montillo A, Ling H. Age regression from faces using random forests. ICIP., 2009 16th IEEE International Conference on 2009 Nov 7 IEEE. p. 2465-8. [DOI]
22. Shotton J, Sharp T, Kipman A, Fitzgibbon A, Finocchio M, Blake A, Cook M, Moore R. Real-time human pose recognition in parts from single depth images. Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 56(1):1297-304. [DOI]
23. Menze BH, Kelm BM, Masuch R, Himmelreich U, Bachert P, Petrich W, Hamprecht FA. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC bioinformatics. 2009;10(1):213. [DOI]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Copyright Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
