Pregled bibliografske jedinice broj: 1025698
Generation of 2D ear dataset with annotated view angles as a basis for angle-aware ear recognition
Generation of 2D ear dataset with annotated view angles as a basis for angle-aware ear recognition // Proceedings of the 28th International Electrotechnical and Computer Science Conference / Andrej Žemva, Andrej Trost (ur.).
Portorož, Slovenija, 2019. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1025698 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Generation of 2D ear dataset with annotated view angles as a basis for angle-aware ear recognition
Autori
Hrovatič, Anja ; Kwon, Kihoon ; Sušanj, Diego ; Peer, Peter ; Emeršič, Žiga
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 28th International Electrotechnical and Computer Science Conference
/ Andrej Žemva, Andrej Trost - , 2019
Skup
International Electrotechnical and Computer Conference
Mjesto i datum
Portorož, Slovenija, 23.09.2019. - 24.09.2019
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Ear recognition ; Ear alignment dataset
Sažetak
Ear recognition has seen steady development in the recent years. Despite numerous novel approaches ranging from traditional approaches based on local feature extraction to deep learning approaches, certain issues still remain unsolved. As pointed out in recent studies, one of the most prominent issues is the problem of ear alignment. To tackle this problem traditional approaches proved to be unsuccessful. However, in order to train deep neural networks to estimate pose angles to facilitate ear alignment, dataset with annotated angles is needed. In this work we present a 2D RGB dataset based on UND-J 3D dataset with corresponding 2D angle-annotated images as a base for convolutional neural network training.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
