A prototype for the automatic measurement of the hand dimensions using the Microsoft Kinect V2

This paper describes a system that allows measuring the geometrical parameters of the human hand starting from the 3D point cloud acquired using a Microsoft Kinect v2 sensor. The measurement system is meant to be used by doctors to identify daily food portion sizes for patients. A LabVIEW based software for data acquisition and data analysis has been developed in order to acquire the point cloud of the hand, to compute the hand parameters needed for the computation of the food portions (hand volume, area, length and width and index height) and to transmit data to a Data Base. The proposed measurement system has been calibrated and algorithms for the compensation of the bias error components were derived. Results evidenced an accuracy better than 1 mm in the identification of the hand dimensions; data are compatible with those reported in the literature for general dimensional measurements.