Title :
Fingerprint Compression by Ridgelet Transform
Author :
Ouanane, Abdelhak ; Serir, Amina
Author_Institution :
Fac. of Electron. & Comput., U.S.T.H.B, Algiers
Abstract :
In the present paper, a concept of compression using block ridgelet transform is introduced. This kind of analysis/synthesis fingerprint representation takes the form of basis elements which exhibit very high directional sensitivity and are highly anisotropic. This transform tailored for fingerprint, associated to a quantized global orientation flow provides a suit representation of the oriented ridges structure. The design and implementation of ridgelet compression scheme are discussed. In order to evaluate the performance of the algorithm, FCV2002, FCV2004 and NIST fingerprint databases have been considered. The results show that this method has a serious potential in fingerprint compression.
Keywords :
data compression; fingerprint identification; image coding; image representation; transforms; FCV2002; FCV2004; NIST; block ridgelet transform; fingerprint compression; fingerprint databases; fingerprint representation; ridgelet compression scheme; Anisotropic magnetoresistance; Data security; Discrete wavelet transforms; Fingerprint recognition; Image coding; Image databases; Image matching; NIST; Quantization; Wavelet transforms; Ridgelet transform; Wavelet Scalar quantization WSQ; fingerprint compression;
Conference_Titel :
Signal Processing and Information Technology, 2008. ISSPIT 2008. IEEE International Symposium on
Conference_Location :
Sarajevo
Print_ISBN :
978-1-4244-3554-8
Electronic_ISBN :
978-1-4244-3555-5
DOI :
10.1109/ISSPIT.2008.4775682
