Locating landmarks on human body scan data

Abstract

Software for locating anthropometric landmarks from a cloud of more than 100000 three dimensional data points, captured from a human subject, is presented. The software is part of an incremental approach that progressively refines the identification of data points. The first phase of identification is to orient and segment the human body data points. Algorithms for these tasks are presented, with a description of their use. One of the algorithms, a discrete point cusp detector is believed to be unique. The software has been tested on twenty different body scan data sets and shown to be robust.