Computational intelligence-based biometric technologies

Computational intelligence (CI) technologies are robust, can be successfully applied to complex problems, are efficiently adaptive, and usually have a parallel computational architecture. For those reasons they have been proved to be effective and efficient in biometric feature extraction and biometric matching tasks, sometimes used in combination with traditional methods. In this article, we briefly survey two kinds of major applications of CI in biometric technologies, CI-based feature extraction and CI-based biometric matching. Varieties of evolutionary computation and neural networks techniques have been successfully applied to biometric data representation and dimensionality reduction. Cl-based methods, including neural 9 network and fuzzy technologies, have also been extensively investigated for biometric matching. Cl-based biometric technologies are powerful when used in the representation and recognition of incomplete biometric data, discriminative feature extraction, biometric matching, and online template updating, and promise to have an important role in the future development of biometric technologies.