Handbook of Multibiometrics

In addition to the match scores provided by the biometric matchers, ancillary information may also be available to a multibiometric system depending on the application scenario. Biometric signal quality and soft biometric information are two examples of such additional information that can be utilized to improve the accuracy of a multibiometric system. While biometric signal quality does not explicitly contain any information about the identity of the user, different biometric matchers exhibit different levels of sensitivity to the quality of the acquired biometric sample. This phenomenon can be exploited in a multibiometric system where the match scores or the identity decisions of the matchers can be appropriately weighted during fusion based on the quality of the input biometric sample. Soft biometric characteristics like gender, ethnicity, height and weight directly provide information about the identity of the user. Although the soft biometric information alone is not sufficient for accurate person recognition, they can be used to complement the information provided by the primary biometric identifiers like fingerprint, iris and face. Techniques for automatically extracting soft biometric information and estimating biometric signal quality have been incorporated into biometric systems only recently. Hence, fusion schemes that incorporate such ancillary information have not been thoroughly explored and there is plenty of scope for conducting more in-depth research in this area.