Pregled bibliografske jedinice broj: 818038
Comparison of RADIAL variance based and Maar- Hildreth operator perceptual image hash functions on biometric templates
Comparison of RADIAL variance based and Maar- Hildreth operator perceptual image hash functions on biometric templates // Central European Conference on Information and Intelligent Systems / Sandra Lovrenčić (ur.).
Varaždin: Fakultet organizacije i informatike Sveučilišta u Zagrebu, 2014. str. 286-292 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 818038 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Comparison of RADIAL variance based and Maar- Hildreth operator perceptual image hash functions on biometric templates
Autori
Vukelić, Bernard ; Bača, Miroslav
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Central European Conference on Information and Intelligent Systems
/ Sandra Lovrenčić - Varaždin : Fakultet organizacije i informatike Sveučilišta u Zagrebu, 2014, 286-292
Skup
Central European Conference on Information and Intelligent Systems - 25th International Conference
Mjesto i datum
Varaždin, Hrvatska, 17.09.2014. - 19.09.2014
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
perceptual hash
Sažetak
This paper presents a practical comparison between two perceptual hash functions, RADIAL Variance Based Hash and Maar-Hildreth Operator. Perceptual image hashing functions are used for image and visual content authentication. For the purposes of this paper the authors will compare the two functions to evaluate their resistance to several types of attacks on biometric templates. The main objective of this paper is to examine whether the implementation of perceptual hash functions could have an effect on similarity of these templates. pHash, an open source implementation of various perceptual hash functions, was used to benchmark these functions. The results of this comparison and evaluation will be preliminary because only three most common biometrics characteristic templates will be considered. Robust perceptual image hashing methods will be used to overcome the abovementioned problems of a challenging developing biometric systems.
Izvorni jezik
Engleski
Znanstvena područja
Informacijske i komunikacijske znanosti