Human Identification from Body Shape

Published

October 1, 2003

Author(s)

Afzal A. Godil, Patrick J. Grother, Sanford P. Ressler

Abstract

In this paper, we investigate the utility of static anthropometric distances as a biometric for human identification. The 3D landmark data from the CAESAR database is used to form a simple biometric consisting of distances between fixed rigidly connected body locations. This biometric is overt, and invariant to view and body posture. We use this to quantify the asymmetry of human bodies, and to characterize the interpersonal and intrapersonal distance distributions. The former is computed directly and the latter by adding zero-mean gaussian noise to the landmark points. This simulation framework is applicable to arbitrary shape based biometric. We use gross body proportions information to model a computer vision recognition system.

Proceedings Title

The Fourth International Conference on 3D Digital Imaging and Modeling

Volume

2003

Issue

4th

Conference Dates

October 1, 2003

Conference Location

Alberta, CA

Conference Title

International Conference on 3D Digital Imaging and Modeling

Pub Type

Conferences

Download Paper

Local Download

Keywords

3D anthropometric, biometric, CAESAR database, GAIT, human identification

Citation

Godil, A. , Grother, P. and Ressler, S. (2003), Human Identification from Body Shape, The Fourth International Conference on 3D Digital Imaging and Modeling, Alberta, CA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=50758 (Accessed October 11, 2025)