A skeleton-free body surface area estimation from depth images using deep neural networks
Darius Nahavandi, Ahmed Abobakr, Hussein Haggag, Mohammed Hossny · 2017
Body surface area is an important measure in many clinical trials. It is a critical parameter that is used in estimating radiation and substance doses for human trials. Traditionally, these trials relied on skin-fold tests which are very invasive and uncomfortable to the subjects. In this paper we present a skeleton-free Kinect system to estimate body surface area of human bodies. The proposed system employs the state-of-the-art deep convolutional network to extract meaningful features and estimate the body surface area with a 12 mm2precision.