Title :
Face database retrieval using pseudo 2D hidden Markov models
Author :
Eickeler, Stefan
Author_Institution :
Fraunhofer Inst. for Media Commun. IMK, Sankt Augustin, Germany
Abstract :
This paper explores the face database retrieval capabilities of a face recognition system based on hidden Markov models (HMMs). A new HMM-based measure to rank images of the database is presented. The method is able to work on a large database. Previous systems for image retrieval based on HMMs were only capable of operating on small databases. The relation of the presented method to confidence measures is pointed out, and five different approximations of the confidence for the task of database retrieval are evaluated. The experiments are carried out on a database of 25,000 different face images, showing that the normalization and filler models are most suitable for retrieval on a large face database
Keywords :
face recognition; hidden Markov models; image retrieval; very large databases; visual databases; confidence approximations; confidence measures; database image ranking; face database retrieval; face recognition system; filler model; large database; normalization model; pseudo-2D hidden Markov models; Discrete cosine transforms; Face recognition; Hidden Markov models; Image databases; Image recognition; Image sampling; Information retrieval; Probability density function; Testing; Transform coding;
Conference_Titel :
Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7695-1602-5
DOI :
10.1109/AFGR.2002.1004133