20.500.12556/RUL-165074 GazeNet a lightweight multitask sclera feature extractor The sclera is a recently emergent biometric modality with many desirable characteristics. However, most literature solutions for sclera-based recognition rely on sequences of complex deep networks with significant computational overhead. In this paper, we propose a lightweight multitask-based sclera feature extractor. The proposed GazeNet network has a computational complexity below 1 GFLOP, making it appropriate for less capable devices like smartphones and head-mounted displays. Our experiments show that GazeNet (which is based on the SqueezeNet architecture) outperforms both the base SqueezeNet model as well as the more computationally intensive ScleraNET model from the literature. Thus, we demonstrate that our proposed gaze-direction multitask learning procedure, along with careful lightweight architecture selection, leads to computationally efficient networks with high recognition performance. biometrics ocular biometrics sclera recognition lightweight feature extraction biometrija očesna biometrija razpoznava beločnice lahki modeli luščenje značilk true false true Angleški jezik Slovenski jezik Članek v reviji 2024-11-22 11:37:28 2024-11-22 11:37:29 2024-11-23 04:05:25 0000-00-00 00:00:00 2025 0 0 Str. 661-671 Vol. 112 Jan. 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.93:57.087.1 1110-0168 10.1016/j.aej.2024.11.011 215847939 RAZ_Vitek_Matej_2025.pdf RAZ_Vitek_Matej_2025.pdf 1 E4D898862C28764C21A6F65C2A395899 db8e00fa67404a6cb7aacfc816d656cb9a3ade0f3d350cf27620b0ae4bd0395a f138e2cd-a8be-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=196028 https://www.sciencedirect.com/science/article/pii/S1110016824014273 1 5f132419-a8bd-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=196027 Fakulteta za računalništvo in informatiko 0 0 0