Overview of Present Work
1.1 Background of present work
The identification of people by measuring some traits of individual anatomy, physiology or other behavioral characteristics has led to a specific research area called biometric recognition. Biometric technologies provide a strong mechanism for authentication and are still under continuous development. Their diffusion is mainly supported by governments, forensics and law enforcement agencies with the aim of improving the public security or in general a sense of security; in fact, the biometric identification does not directly improve the security but acts as deterrent to illegal activities.The application of biometrics in forensics has a long history and can be considered as the big bang of the biometric recognition world. Alphonse Bertillon, chief of the criminal identification division of the police department in Paris, developed and then practiced the idea of using a number of body measurements to identify criminals in the mid-19th century. In the twentieth century law enforcement agencies have extensively used biometrics for security purposes. In the last years, the adoption of biometrics has met a large increase even in general purpose applications, due mainly to a combination of the falling cost of biometric devices, increasing sophistication of the technology and development of biometrics as a peripheral to common computer platforms. Several bio- metrics have been successfully developed and deployed: fingerprints, face, iris, voice and palmprints are the most currently used.Fingerprints are the main biometric trait discussed in this Thesis.
fingerprint orientation extraction, fingerprint enhancement and automatic evaluation of fingerprint algorithms.Fingerprint orientation extraction and fingerprint enhancement can be considered as pre-processing steps to the main goal of the fingerprint recognition problem: the com- parison with other fingerprints. More clear are the characteristics we can extract from a fingerprint, more reliable is the output of a comparison between fingerprints (matching).The automatic evaluation of fingerprint recognition algorithms over common databases is very important in order to assess the performance of various algorithms and understand the most effective and promising building block technologies.In this introductory chapter we present the basics of biometric systems describing the characteristics of the most common biometric traits. Fingerprints, that are the core of this Thesis, are described in detail in the next chapter. This chapter is finished provid- ing the motivations and goals of this Thesis, the novel contributions to the fingerprint recognition field and describing the organization of the Thesis such that a reader can easily navigate among chapters.