Can computer vision be used for anthropometry? A feasibility study of a smart mobile application

Abstract

Anthropometry is a method for measuring physical characteristics of the human body, particularly dealing with measures of size and shape of the body. These measurements can be performed using a tape measure, but new devices and software solutions already been employed in digital anthropometry. However, such tools do not enable the anthropometric evaluation to be performed automatically. In this paper, we present the NLMeasurer application for anthropometry, a mobile tool based on computer vision for identifying anatomical reference points (ARPs) and assessing the size of body segments. To evaluate the performance of the NLMeasurer, four participants were photographed and their images processed. The anthropometric measures calculated by the application, using different settings, were compared with those obtained using a tape measure. Results indicate no statistically significant difference ($\\mathrm{p} > 0.05$) between the methods, except in one configuration. This initial experiment was promising to reveal the feasibility of using NLMeasurer for anthropometry.