User authentication (identity verification) and encryption have great significance for computer network security. Public key cryptography provides a secure way to exchange information but designing a high security user authentication system still remains an open problem. The conventional means of identification (e.g., passwords, personal identification numbers can be easily guessed, observed or forgotten.
An increasing number of services over the Internet require a reliable means of authentication of users. Examples of these are e-commerce, financial services (e.g., banking), access to confidential information (e.g., patient's medical record file) etc.
Several of the biometric characteristics of an individual are unique and time invariant. These properties make biometrics well suited for user identification or verification.
Biometrics is an emerging technology that identifies users by their physical and/or behavioural characteristics, and inherently requires that the user to be identified is physically present at the point of identification. The physical characteristics of an individual that are used in identification/verification systems based on biometrics are as follows: fingerprint, hand geometry, palmprint, face, iris, retina, and ear. The behavioural characteristics are: signature, lip movement, speech, keystroke dynamics, gesture and gait. Biometric systems based on a single biometric characteristic are unimodal systems. They are usually more cost-efficient then multimodal biometric systems. However, a single physical characteristic of an individual sometimes fails to be sufficient for identification, for this reason multimodal biometric systems, which integrate two or more different biometric characteristics are being developed to provide an acceptable performance, to increase reliability of decisions and to increase robustness to fraudulent technologies.
The aim of the project is development a prototype of biometric system for Internet user authentication based on fusion of face and palmprint features. The main phases of the projects are:
- Designing experimental database of faces and palmprints;
- Development of software modules for face detection, localization and face normalization;
- Template generation (for face and palmprint);
- Development of recognition procedures;
- Fusion at the matching-score level;
- Defining the enrolment and identification/verification procedures;
- System testing (FAR and FRR);