INFORMATION SOURCES FOR MULTIBIOMETRIC SYSTEMS

                               Growth of a multibiometric system for security purposes is not an inconsequential job. As with any unimodal scheme, the data attainment process, sources of information, level of predictable accuracy, system sturdiness, user training, data privacy, and dependence on proper implementation of hardware and proper prepared procedures impact directly the presentation of security system. While using more than one data starting place alleviates some issues (such as noisy data, missing samples, errors in acquisition, spoofing etc.), this improvement does not come free. The choice of biometric information that needs to be incorporated or fused must be made, information fusion method should be selected, cost vs. benefit psychoanalysis needs to be performed, processing.

                              For many applications, there are supplementary sources of non-biometric information that can be used for person verification, while in others the use of a single biometric is not adequately secure or does not provide adequate coverage of the user population. This can be indicated by such limitation as Failure to Enroll rate. Thus, multibiometric system emerged as a way to provide more secure and dependable person verification system under those conditions.

                               It must be pointed out that in literature there is a insignificant difference between two terms. The term multimodal biometric system refers particularly to those biometric systems where more than one biometric modalities are used. The term multibiometric is more generic and includes multimodal systems and some other configurations using only one biometric modality with different samples instances or algorithms.

                            Information fusion can be distinct as “an information process that associates, correlates and combines data and information from single or multiple sensors or sources to achieve refined estimates of parameters, characteristics, events and behaviors”. A good information fusion method allows the impact of less reliable sources be lowered compared to reliable ones. A number of dissimilar research areas including robotics, image dispensation, pattern acknowledgment, information reclamation etc. utilize and describe information fusion in their context. Thus, information fusion recognized itself as an independent research area over the last decade for its impact on a vast number of dissimilar data and feature fusion