Adaptive Spatial Transformation Networks for Periocular Recognition
Author:
Borza Diana Laura1, Yaghoubi Ehsan2, Frintrop Simone2, Proença Hugo3ORCID
Affiliation:
1. Informatics Department, Faculty of Mathematics and Informatics, Babes Bolyai University, 1st Mihail Kogalniceanu Street, 400084 Cluj-Napoca, Romania 2. Department of Informatics, Hamburg University, 177 Mittelweg, 20148 Hamburg, Germany 3. IT: Instituto de Telecomunicações, University of Beira Interior, Marquês de Ávila e Bolama, 6201-001 Covilhã, Portugal
Abstract
Periocular recognition has emerged as a particularly valuable biometric identification method in challenging scenarios, such as partially occluded faces due to COVID-19 protective masks masks, in which face recognition might not be applicable. This work presents a periocular recognition framework based on deep learning, which automatically localises and analyses the most important areas in the periocular region. The main idea is to derive several parallel local branches from a neural network architecture, which in a semi-supervised manner learn the most discriminative areas in the feature map and solve the identification problem solely upon the corresponding cues. Here, each local branch learns a transformation matrix that allows for basic geometrical transformations (cropping and scaling), which is used to select a region of interest in the feature map, further analysed by a set of shared convolutional layers. Finally, the information extracted by the local branches and the main global branch are fused together for recognition. The experiments carried out on the challenging UBIRIS-v2 benchmark show that by integrating the proposed framework with various ResNet architectures, we consistently obtain an improvement in mAP of more than 4% over the “vanilla” architecture. In addition, extensive ablation studies were performed to better understand the behavior of the network and how the spatial transformation and the local branches influence the overall performance of the model. The proposed method can be easily adapted to other computer vision problems, which is also regarded as one of its strengths.
Funder
German Science Foundation FCT/MCTES
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference41 articles.
1. Damer, N., Grebe, J.H., Chen, C., Boutros, F., Kirchbuchner, F., and Kuijper, A. (2020, January 16–18). The effect of wearing a mask on face recognition performance: An exploratory study. Proceedings of the 2020 International Conference of the Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany. 2. Woodard, D.L., Pundlik, S.J., Lyle, J.R., and Miller, P.E. (2010, January 13–18). Periocular region appearance cues for biometric identification. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, San Francisco, CA, USA. 3. Periocular biometrics and its relevance to partially masked faces: A survey;Sharma;Comput. Vis. Image Underst.,2023 4. Human and machine performance on periocular biometrics under near-infrared light and visible light;Hollingsworth;IEEE Trans. Inf. Forensics Secur.,2011 5. Park, U., Ross, A., and Jain, A.K. (2009, January 28–30). Periocular biometrics in the visible spectrum: A feasibility study. Proceedings of the 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems, Washington, DC, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|