Biometric systems

Recently the world has seen an increasing activity in biometrics for both the defense and security related applications and the commercial applications such as e-commerce. Biometrics such as fingerprints, face, gait, iris, voice, signature, etc. recognize a person's identity using his/her physiological or behavioral characteristics. These biometrics are needed for reliable and positive identifications of an individual beyond the transitional password and identifications numbers, which may not be reliable. Among these biometric signs, fingerprints is the one, which has been researched for a long time and shows the most promising future in real-world applications.

Biometrics are rapidly making their way into the mainstream as a means to help prevent identity theft and fraud.  Most visibly, we see fingerprint sensors being integrated into smart phones as a more convenient mode of secure access to a device for its owner.

These devices are increasingly enabling use of biometrics towards more secure mobile payment models that aim to avoid security pitfalls of credit cards. Biometric authentication functionality is used in government and commercial applications supporting fingerprint, face, and iris modalities. With people, crossing state borders numbers continually on the rise, passengers, immigrants, refugees increasing in size, and consciousness of security issues coming to the forefront, border control, visas approval, technology and infrastructure worldwide are now facing major challenges.

Biometrics is growing, because our fingerprints, faces, irises, and voices have truly special properties that make them an effective barrier to fraudsters attempting to surreptitiously impersonate us. They are useful because unlike names, ID numbers, email addresses, and passwords, they are comparatively more unique, secret, permanent, consistent, difficult to reproduce.

We are developing and maintaining biometrics applications in a comprehensive view, backend/frontend application, biometrics database design and implementation, and also maintenance of our own systems or third party biometrics systems. 

Our research is focused to Genetic Programming based feature for fingerprint classification. Genetic Programming is used in a novel manner to discover composite operators and associated features that are evolved from combinations of primitive operators and primitive features. Primitive features, based on the orientation image, allow the incorporation of domain knowledge into the evolutionary computational process.

A biometric engine is the core program that controlls the different hardware and components of a biometric system. The biometric engine controls the enrollment, capture, extraction, comparison and matching of biometric data from a user.

It is based on a set of algorithms that facilitate the steps in the recognition process, as well as the intermediary processes like image enhancement, determining quality and the extraction of distinguishing features.

It is the efficiency of this engine that dictates the quality of the system. Even with state of the art hardware, if the biometric engine is not functioning correctly, then the system will get many errors and false readings or identifications.

The biometric engine will also enhance the data taken, enhancing images and clearing out noise so that what is left is clear data. Thus, the data becomes easy to match whenever an enrollee needs to be authenticated.

tip"A biometric system is a technological system that uses information about a person (or other biological organism) to identify that person. Biometric systems rely on specific data about unique biological traits in order to work effectively. A biometric system will involve running data through algorithms for a particular result, usually related to a positive identification of a user or other individual."