MODEL-BASED BIOMETRICS

Identifying patterns in behavioral biometrics, in general, is a slightly different and somewhat more complex problem than identifying features in physiological biometrics. Examples of behavioral biometrics include signature, voice, gait, and typing patterns. Due to temporal dynamic features associated with each biometric (samples must be observed over period of time for best matching results), these problems are often treated in a class of signal-processing methods. In a nutshell, the task and the overall biometric system architecture remain the same; however upon closer examination; some very specialized methods taking advantage of unique continuous nature of that biometrics have been developed.

Different image processing methods and algorithms that are popular in biometric data processing has been presented. In the case of the most of the biometric identifiers used today, image of that identifier is mainly the input to the biometric system. Thus, the processing of the biometric images is very essential for efficient and reliable performance of the biometric system. Usually, the main methods which are used for biometric image processing are digitization, compression, enhancement, segmentation, feature measurement, image representation, image models and design methodology. The feature extraction methods have been classified as appearance-based and topological feature-based, and illustrated on example of different fingerprint recognition

The optimal biometric system is one having the properties of distinctiveness, universality, permanence, acceptability, collectability, and security. As we saw in the introductory chapters, no existing biometric security system simultaneously meets all of these requirements. Despite tremendous progress in the field, over the last decades researchers noticed that while a single biometric trait might not always satisfy secure system requirements, the combination of traits from different biometrics will do the job. The key is in aggregation of data and intelligent decision making based on responses received from individual (unimodal) biometric systems.

Thus, Multimodal biometrics emerged as a new and highly promising approach to biometric knowledge representation, which strives to overcome problems of individual biometric matchers by consolidating the evidence presented by multiple biometric traits. As an example, a multimodal system may use both face recognition and signature to authenticate a person. Due to reliable and efficient security solutions in the security critical applications, multimodal biometric systems have evolved over last decade as a viable alternative to the traditional unimodal security systems.