Akademik Veri Yönetim Sistemi
3rd IAPR Workshop on Artificial Neural Networks in Pattern Recognition, Paris, Fransa, 2 - 04 Temmuz 2008, cilt.5064, ss.305-307
Biometrics technology has received increasingly more attention during the last three decades. Since the performance of biometric systems has reached a satisfactory level for applications, a number of biometric features have been deeply studied, tested and successfully deployed in applications. Relationships among biometric features have not been studied so far. This study focuses on analysing the existence of any relationships among fingerprints and faces. For doing that an intelligent system based on artificial neural networks for generating face models including eyes, nose, mouth, ears and face border from only one fingerprint with the errors among 2.0-12.9% was developed. Experimental results have shown that there are close realitionships among fingerprints and faces and it is possible to generate faces from only one fingerprint image without knowing any information about faces. Although the proposed system is an initial study and it is still under development, the results are very encouraging and promising for the future developments and applications.