Title :
Digital signal processing in biometric identification: a review
Author :
Wayman, James L.
Author_Institution :
Coll. of Eng., San Jose State Univ., CA, USA
Abstract :
In this context, "biometrics" is the "automatic identification or identity verification of living, human individuals based on physiological and behavioral characteristics". Biometrics is a subset of the larger field of human identification science. The term "automatic" in the definition means that digital computers will usually (but not always) be used. We consider the general state of digital signal processing in biometrics by examining the computational approaches to speaker, fingerprint, and face recognition. We note the generally weak relationship between physiology and biometric "features" and the potential for use of "models" to compensate for intra-class variation.
Keywords :
behavioural sciences computing; biometrics (access control); face recognition; feature extraction; physiology; signal processing; speaker recognition; automatic identification; behavioral characteristics; biometric identification; digital signal processing; face recognition; fingerprint recognition; human identification science; identity verification; intra-class variation compensation; physiological characteristics; physiology; speaker recognition; Analog computers; Biomedical signal processing; Biometrics; Digital signal processing; Face recognition; Feature extraction; Fingerprint recognition; Humans; Multidimensional signal processing; Quality control;
Conference_Titel :
Image Processing. 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7622-6
DOI :
10.1109/ICIP.2002.1037953