Fusion of gait and face for human identification
Authors:
- R. ChellappaRCR. Chellappa
- 28 September 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5, 901
Abstract
Identification of humans from arbitrary view points is an important requirement for different tasks including perceptual interfaces for intelligent environments, covert security and access control etc. For optimal performance, the system must use as many cues as possible and combine them in meaningful ways. In this paper we discuss fusion of face and gait cues for the single camera case. We present a view invariant gait recognition algorithm for gait recog- nition. We employ decision fusion to combine the results of our gait recognition algorithm and a face recognition algorithm based on sequential importance sampling . We consider two fusion sce- narios: hierarchical and holistic. The first involves using the gait recognition algorithm as a filter to pass on a smaller set of candi- dates to the face recognition algorithm. The second involves com- bining the similarity scores obtained individually from the face and gait recognition algorithms Simple rules like the SUM, MIN and PRODUCT are used for combinining the scores. The results of fusion experiments are demonstrated on the NIST database which has outdoor gait and face data of 30 subjects.Keywords
This publication has 8 references indexed in Scilit:
- Integrated face and gait recognition from multiple views2005
- Towards a view invariant gait recognition algorithm2004
- Face reconstruction from monocular video using uncertainty analysis and a generic modelComputer Vision and Image Understanding, 2003
- Probabilistic recognition of human faces from videoComputer Vision and Image Understanding, 2003
- On probabilistic combination of face and gait cues for identification2003
- Gait Analysis for Human Identification2003
- On combining classifiersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991