Body Mass Index Classification based on Facial Features using Machine Learning Algorithms for utilizing in Telemedicine

Background and Objectives: Due to the impact of controlling BMI on life, BMI classification based on facial features can be used for developing Telemedicine systems and eliminating the limitations of measuring tools, especially for paralyzed people. So that physicians can help people online during the Covid-19 pandemic. Method: 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 are 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's 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's best performance was in women's group (94.84%), square-face and round-face groups (84.12% and 84% respectively). Conclusion: The 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 handicapped people.