20.500.12556/RUL-176531 Synthesizing multilevel abstraction ear sketches for enhanced biometric recognition Sketch understanding poses unique challenges for general-purpose vision algorithms due to the sparse and semantically ambiguous nature of sketches. This paper introduces a novel approach to biometric recognition that leverages sketch-based representations of ears, a largely unexplored but promising area in biometric research. Specifically, we address the “sketch-2-image” matching problem by synthesizing ear sketches at multiple abstraction levels, achieved through a triplet-loss function adapted to integrate these levels. The abstraction level is determined by the number of strokes used, with fewer strokes reflecting higher abstraction. Our methodology combines sketch representations across abstraction levels to improve robustness and generalizability in matching. Extensive evaluations were conducted on four ear datasets (AMI, AWE, IITDII, and BIPLab) using various pre-trained neural network backbones, showing consistently superior performance over state-of-the-art methods. These results highlight the potential of ear sketch-based recognition, with cross-dataset tests confirming its adaptability to real-world conditions and suggesting applicability beyond ear biometrics. ear biometrics sketch-based identification triplet-loss function cross-dataset generalizability biometrija uhljev identifikacija na podlagi skice trojnoizgubna funkcija splošna prenosljivost med podatkovnimi nabori true false true Angleški jezik Slovenski jezik Članek v reviji 2025-12-03 08:37:26 2025-12-03 08:37:27 2025-12-22 03:57:22 0000-00-00 00:00:00 2025 0 0 10 str. art. 105424 Vol. 154 Feb. 2025 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 004.93:57.087.1 0262-8856 10.1016/j.imavis.2025.105424 258163715 RAZ_Freire-Obregon_David_2025.pdf RAZ_Freire-Obregon_David_2025.pdf 1 EDAE253F8F19A59E64D3935E1B8822B9 9eaece27b699e4178808f8460b1f2a54d31d53a6194621a8d4a7d76c9d369df0 7c662fe1-d01d-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=222913 https://www.sciencedirect.com/science/article/pii/S0262885625000125 1 8821d782-d01a-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=222911 Fakulteta za računalništvo in informatiko 0 0 0