Abstract—Traditional personal authentication systems that are based on knowledge (e.g., password) or physical tokens (e.g., ID card) are not able to meet strict security performance requirements of a number of modern applications. Biometric-based authentication systems that use physiological and/or behavioral traits (e.g., fingerprint, face and signature) are good alternatives to traditional methods. These systems are more reliable (biometric data cannot be lost, forgotten or guessed) and more user-friendly (there is nothing to remember or carry). In spite of these advantages of biometric systems over traditional systems, there are many unresolved issues associated with the former. In this article, we analyze structure of biometric-based authentication systems and vulnerability of these systems and develop a method for increasing the security of image-based (e.g., fingerprint and face) biometric templates. We use a method based on fractal image coding for face and fingerprint recognition. We create a database from fractal codes of biometric images. For identification the input image is decoded with each fractal code in the database. The fractal code that minimizes the Euclidian difference between the input image and the result image after one iteration of decoding is taken as the best. We used this method for fingerprint and face recognition. Similar methods for face recognition have been proposed by others, but what distinguishes our work from the rest is that we improve the recognition rate needles to execution same complicated preprocessing. Other advantages of this method are: increasing security because use of fractal codes instead of original images, and acceptable result in face recognition in spite of different face expression.

Index Terms—Authentication, Biometric Template, Fractal Image Coding, Security

F. A. Atiya zahed is with Computer & Electronic Department,Islamic Azad University Branch of Kashan, Iran (e-mail: a.zahed@iaukashan.ac.ir).
S. B. Mohammad Reza Sakhi is with Computer & Electronic Department,Islamic Azad University Branch of Kashan, Iran (e-mail: m.r.sakhi@iaukashan.ac.ir).

Cite: Atiya Zahed and Mohammad Reza Sakhi, "A Novel Technique for Enhancing Security in Biometric Based Authentication Systems," International Journal of Computer and Electrical Engineering vol. 3, no. 4, pp. 520-523, 2011.