Title :
Impact of PCA based fingerprint compression on matching performance
Author :
Stojanovic, Boban ; Neskovic, Aleksandar
Author_Institution :
Vlatacom d.o.o., Belgrade, Serbia
Abstract :
This paper deals with the compression of fingerprints and the impact of compression on matching (recognition) performance. PCA method with the compression ratio 2.18:1 is proposed for fingerprints compression. Fingerprints compressed in this manner and the original (uncompressed) fingerprints were matched (1:n identification) with the fingerprints database which consists of 120 samples. Based on the matching scores the FRR and FAR values were calculated. These values show the impact of the compression on matching performance.
Keywords :
fingerprint identification; image coding; image matching; principal component analysis; FAR value; FRR value; PCA based fingerprint compression; matching performance; recognition performance; Biometrics (access control); Electronic mail; Fingerprint recognition; Image coding; Matrix decomposition; Principal component analysis; Singular value decomposition; FAR; FRR; PCA; kompresija; otisci; poredenje;
Conference_Titel :
Telecommunications Forum (TELFOR), 2012 20th
Conference_Location :
Belgrade
Print_ISBN :
978-1-4673-2983-5
DOI :
10.1109/TELFOR.2012.6419304
