Depth Dataset Using Microsoft Kinect-v2

Abstract

In biomedical imaging studies, numerous methods have been used to capture human data, mostly by using magnetic resonance imaging (MRI) and computed tomography (CT). However, due to being inexpensive and accessibility of Microsoft Kinect, its usage has been significantly increased in recent years. In this study, we aimed to represent the procedure of data acquisition, which includes a set of depth images from individuals back surfaces. The goal of image acquisition is to investigate spinal deformities and landmark detection of the back surface. Traditional imaging systems are challenging, most notably because of ionized beams in the data acquisition process, which has not been solved yet. Indeed, noninvasiveness is the most crucial advantage of our study. Our imaging system was set in a dim laboratory, and the University approved the ethical letter of Medical Sciences before data acquisition. After that, the subjects (total 105; 50 women and 55 men) were recruited, and data images were captured from the back surface. Then, we increased the imaging data size by using the augmentation method to use deep learning methods in future works. Finally, this Dataset leads us to the desired output in our study procedure.