Naslov
Palmprint Recognition Based on Local Texture Features

Autori
Ribarić, Slobodan ; Lopar, Markan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Machine Learning and Data Mining in Pattern Recognition / Prof. Dr. Petra Perner (ed.) - Fockendorf : Ibai-publishing, 2013, 119-127

Skup
Machine Learning and Data Mining in Pattern Recognition, 9th International Conference, MLDM 2013, International Workshop on "Intelli-gent Pattern Recognition and Applications” WIPRA'2013

Mjesto i datum
Sjedinjene Američke Države, 15.07.2013. - 24.07.2013

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Palmprint recognition; local Haralick features; Open set identification

Sažetak
In this paper, we propose and evaluate palmprint recognition method based on local Haralick features. The Haralick features are extracted from over-lapping square subimages of a palmprint region of interest (ROI). A biometric template is composed of N m-component feature vectors, where N is the total number of overlapping subimages, and m is the number of local Haralick fea-tures per subimage in the ROI. A live biometric template and templates from database are matched in N matching modules. Based on fusion at the matching-score level, the total similarity measures between a live biometric template and templates from the database are calculated. By using the maximum of total similarity measure and the 1-NN classification rule, the final decision (person identity) is made. The proposed palmprint recognition system was tested on the PolyU database. The results of open set identification are given.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA