การประมาณ ส่วนสูง น้ำหนัก และ ดัชนีมวลกาย โดยใช้ภาพถ่ายร่างกายมนุษย์

Abstract

This research primarily aims to develop a system that uses machine learning technology to predict human height, weight, and body mass index from images. The researcher proposes a method that utilizes the PiFuHD model to transform 2D photos into 3D, along with processes for feature extraction, feature selection, and a 3D image noise reduction system, for training and testing machine learning models. Data were collected from a survey of male and female Thai volunteers aged 18 to 65, without physical disabilities, to evaluate their prediction abilities for height, weight, and body mass index. The effectiveness and accuracy of the machine learning methods were assessed using performance metrics such as mean absolute error, root mean square error, and the coefficient of determination. Results showed a mean absolute error of 4.38 centimeters for height prediction, 8.56 kilograms for weight prediction, and a body mass index of 3.03 in the test set. This research opens avenues for researchers and interested parties to utilize the developed concepts and methods in creating applications or systems capable of efficiently predicting human height, weight, and body mass index from images.