Precise and Automatic Anthropometric Measurement Extraction using Template Registration
Oliver Wasenmüller, Jan C. Peters, Vladislav Golyanik, Didier Stricker
Proceedings of the 6th International Conference on 3D Body Scanning Technologies International Conference on 3D Body Scanning Technologies (3DBST-2015), October 27-28, Lugano, Switzerland

Abstract:

Anthropometric measures build the basis for many applications, such as custom clothing or biometric identity verification. Consequentially, the possibility to automatically extract them from human body scans is of high importance. In this paper we present a new approach based on landmarks and template registration. First, we propose a new method to define anthropometric measures once on a generic template using landmarks. After the initial definition the template can be registered against an individual body scan and the landmarks can be transferred to the scan using our second proposed algorithm. We apply our complete approach to real and synthetic human data and show that it outperforms the state-of-the-art for several measures.

Precise and Automatic Anthropometric Measurement Extraction using Template Registration
(Hrsg.)
Proceedings of the 6th International Conference on 3D Body Scanning Technologies International Conference on 3D Body Scanning Technologies (3DBST), October 27-28, Lugano, Switzerland

Abstract:

Anthropometric measures build the basis for many applications, such as custom clothing or biometric identity verification. Consequentially, the possibility to automatically extract them from human body scans is of high importance. In this paper we present a new approach based on landmarks and template registration. First, we propose a new method to define anthropometric measures once on a generic template using landmarks. After the initial definition the template can be registered against an individual body scan and the landmarks can be transferred to the scan using our second proposed algorithm. We apply our complete approach to real and synthetic human data and show that it outperforms the state-of-the-art for several measures.