Software Approach to BMI and Obesity Determination using Facial Extraction Techniques

Abstract

The focus on COVID-19 pandemic has led doctors to reduce consultation and restrict hospital visitations by patients, a decision that has resulted in the increased cases of obesity coupled with restrictions on movement and exercises. Obesity places the health of people in danger, since it is associated with poor mental health, reduce quality of life, increases the risk of diabetes, heart disease, stroke and introduces certain types of cancer. The aim of this study therefore is to design and develop a face-to-BMI mobile application that enable people to learn about their Body Mass Index (BMI), get their obesity status, as well as receive doctor recommendations (or counsel) from the comfort of their homes using their mobile devices. The design science research methodology was used in the design and development of the mobile application for obesity assessment. A mobile phone is required to take the face photo of the users after which the algorithm will perform face detection, looking for all possible facial features such as the width-to-upper facial height ratio (WHR), cheek-to-jaw width (WJWR), perimeter of area ratio (PAR), lower face to face height ratio (FW/FH), mean of eyebrow height (MEH) using facial measurements such as the iris, mouth corners, eyebrows, and nostril. The algorithm then performs Active Shape Model (ASM) fitting. The mobile app was tested with five (5) participants and the results have shown significant improvement in obesity detection and ease of use