Date of Graduation
Statler College of Engineering and Mineral Resources
Lane Department of Computer Science and Electrical Engineering
Arun Abraham Ross.
Multimodal biometric systems utilize the evidence presented by multiple biometric modalities (e.g., face and fingerprint, multiple fingers of a user, multiple impressions of a single finger, etc.) in order to determine or verify the identity of an individual. Information from multiple sources can be consolidated in three distinct levels : (i) feature set level; (ii) match score level; and (iii) decision level. While fusion at the match score and decision levels have been extensively studied in the literature, fusion at the feature level is a relatively understudied problem. A novel technique to perform fusion at the feature level by considering two biometric modalities---face and hand geometry, is presented in this paper. Also, a new distance metric conscripted as the Thresholded Absolute Distance (TAD) is used to help reinforce the system's robustness towards noise. Finally, two techniques are proposed to consolidate information available after match score fusion, with that obtained after feature set fusion. These techniques further enhance the performance of the multimodal biometric system and help find an approximate upper bound on its performance. Results indicate that the proposed techniques can lead to substantial improvement in multimodal matching abilities.
Govindarajan, Rohin K., "Feature-level fusion in multimodal biometrics" (2004). Graduate Theses, Dissertations, and Problem Reports. 1489.