A system f o r face recognition using range images as input data is described. The range data acquisition procedure is based on the coded light approach, merging range images that are recorded by two separate sensors. Two approaches, which are known from face recognition based o n grey level images, have been extended to dealing with range images. These approaches are based on eigenfaces and hidden Markov models, respectively. Experimental results on a database with various range images from 24 persons show very promising results for both recognition methods.

No abstract

No abstract

I n this paper we present a system for person identification which is based o n the combination of several face classifiers. First, we shortly describe the individual face classifiers. Then, classifier combination is discussed. Finally, the impact of the combination is presented in a series of practical experiments which show a significant improvement of the recognition rate.

No abstract