Razpoznava oseb na podlagi biometričnih podatkov uhljev

Emeršič, Žiga (author), Peer, Peter (mentor), Štruc, Vitomir (co-mentor)

Na področju biometrije uhljev, kljub razvoju v zadnjih letih, ni na voljo nobenega prosto dostopnega orodja ali podatkovne baze, zajete v nekontroliranem okolju, ki bi olajšal primerjavo metod za razpoznavo oseb na podlagi uhljev. V okviru tega dela je bila pripravljena nova baza uhljev, ki je zajeta v nekontroliranem okolju, orodje za razpoznavo uhljev in metoda rotacijsko invariantne kvantizacije lokalne faze, ki na uhljih še ni bila uporabljena, skupaj s fuzijo te metode z vektorji normiranih slik. Rezultati metode so primerljivi, vendar ne boljši od trenutno najboljših, smo pa s fuzijo dosegli boljše rezultate kot s samo metodo rotacijske invariantne kvantizacije lokalne faze. Razvito orodje za razpoznavo uhljev predstavlja korak k standardizaciji na področju razpoznave uhljev, testi na bazi uhljev pa so pokazali, da baza predstavlja večji izziv od obstoječih, a je hkrati primerljiva in je zato primerna za nadaljno rabo.

• Language: Slovenian
• Keywords: uhlji, biometrija, razpoznava oseb, razpoznava oseb na podlagi uhljev, biometrični podatki uhljev, podatkovna baza uhljev, orodje za uhlje, orodje za razpoznavo uhljev računalniški vid
• Work type: Master's thesis/paper
• Organization: FRI - Faculty of Computer and Information Science
• Year: 2015
• PID: 20.500.12556/RUL-72426
• Publication date in RUL: 17.09.2015

Secondary language

• Language: English
• Title: Human recognition based on ear biometric data

Abstract

In the field of ear biometrics, despite recent developments, there are no freely available tools or databases captured in the wild that would ease the comparison of methods for ear biometric recognition. A new ear database captured in the wild was developed as a part of this thesis as well as a new toolbox for ear recognition. Rotation invariant local phase quantization method was also applied, for the first time in the field of ear biometrics, together with a fusion of this method with vectors of normalized images. Results are comparable but not better than the state-of-the-art, however, with the fusion we have achieved better results than the rotation invariant local phase quantization alone. The developed toolbox for ear recognition presents a new step towards standardization in the field of ear recognition and tests on the ear database have shown that the database presents greater challenge than the existing ones, but it is still comparable, which makes it suitable for further use.

• Keywords: ear, ears, biometric, biometrics, human recognition base on ears, ear biometric data, ear database, ear toolbox, ear recognition toolbox, computer vision