University of Houston

The integration of biometric technologies with authentication systems allows us to distinguish individuals easier, faster, and in a more secure manner. As a result, biometric authentication is becoming increasingly important for various applications such as access control and financial transactions. However, despite the encouraging results obtained in controlled environments, biometric authentication remains a challenging problem in real-life conditions. Regardless of whether a biometric system relies on face, fingerprint, or any other biometric trait, it must perform: (i) feature-level matching to generate matching scores that reflect the degree of similarity of the biometric samples matched; and (ii) score-level processing to generate improved matching scores. Depending on the biometric modality used, different challenges arise that degrade the recognition performance including: (i) distortions due to the different data acquisition conditions; (ii) artifacts introduced by pre-processing algorithms; (iii) incomplete utilization of the available information; and (iv) having to match data from distinct domains.

The goal of this research is to develop new matching algorithms and score processing methods that increase the recognition performance of all biometric systems irrespective of the biometric trait used. The specific objectives are to develop: (i) one-to-one matching algorithms for samples from the same and distinct domains; and (ii) score normalization algorithms for unimodal and multimodal systems that utilize multiple samples per subject, gallery-based information, and past experiences to improve the system’s performance.