Visual filters for face recognition

Author

Takács, Barnabás ; Wechsler, Harry

Author_Institution

WaveBand Corp., Torrance, CA, USA

fYear

1996

fDate

14-16 Oct 1996

Firstpage

218

Lastpage

223

Abstract

The authors describe a general approach for the multiscale representation, detection, and recognition of object primitives as it applies to face recognition tasks. The approach is based on radially non-uniform sampling strategy, and a local light adaptation mechanism for low-level image representation. Early processing involves feature encoding and classification using visual filter banks implemented via self-organizing feature maps (SOFM). Optimal filters are constructed by means of an iterative, crossvalidation-like data reduction algorithm. The derived visual filter representation is applicable to both (i) facial landmark detection, and (ii) face identification. Experimental results on a data set of over 200 images prove the feasibility of their approach

Keywords

biometrics (access control); data reduction; face recognition; filters; image classification; image coding; image recognition; image representation; face identification; face recognition; facial landmark detection; feature classification; feature encoding; iterative cross-validation-like data reduction algorithm; local light adaptation mechanism; low-level image representation; multiscale detection; multiscale recognition; multiscale representation; object primitives; optimal filters; radially nonuniform sampling strategy; self-organizing feature maps; visual filter banks; visual filters; Character recognition; Face detection; Face recognition; Feature extraction; Filter bank; Humans; Image recognition; Image resolution; Lighting; Signal resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on

Conference_Location

Killington, VT

Print_ISBN

0-8186-7713-9

Type

conf

DOI

10.1109/AFGR.1996.557267

Filename

557267