Academic Journal

UCDCN: a nested architecture based on central difference convolution for face anti-spoofing

التفاصيل البيبلوغرافية
العنوان: UCDCN: a nested architecture based on central difference convolution for face anti-spoofing
المؤلفون: Zhang, Jing, Guo, Quanhao, Wang, Xiangzhou, Hao, Ruqian, Du, Xiaohui, Tao, Siying, Liu, Juanxiu, Liu, Lin
المساهمون: National Natural Science Foundation of China, Fundamental Research Funds for Central Universities of the Central South University, Fundamental Research Funds for the Central Universities
المصدر: Complex & Intelligent Systems ; ISSN 2199-4536 2198-6053
بيانات النشر: Springer Science and Business Media LLC
سنة النشر: 2024
الوصف: The significance of facial anti-spoofing algorithms in enhancing the security of facial recognition systems cannot be overstated. Current approaches aim to compensate for the model’s shortcomings in capturing spatial information by leveraging spatio-temporal information from multiple frames. However, the additional branches to extract inter-frame details increases the model’s parameter count and computational workload, leading to a decrease in inference efficiency. To address this, we have developed a robust and easily deployable facial anti-spoofing algorithm. In this paper, we propose Central Difference Convolution UNet++ (UCDCN), which takes advantage of central difference convolution and improves the characterization ability of invariant details in diverse environments. Particularly, we leverage domain knowledge from image segmentation and propose a multi-level feature fusion network structure to enhance the model’s ability to capture semantic information which is beneficial for face anti-spoofing tasks. In this manner, UCDCN greatly reduces the number of model parameters as well as achieves satisfactory metrics on three popular benchmarks, i.e., Replay-Attack, Oulu-NPU and SiW.
نوع الوثيقة: article in journal/newspaper
اللغة: English
DOI: 10.1007/s40747-024-01397-0
DOI: 10.1007/s40747-024-01397-0.pdf
DOI: 10.1007/s40747-024-01397-0/fulltext.html
الاتاحة: http://dx.doi.org/10.1007/s40747-024-01397-0
https://link.springer.com/content/pdf/10.1007/s40747-024-01397-0.pdf
https://link.springer.com/article/10.1007/s40747-024-01397-0/fulltext.html
Rights: https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0
رقم الانضمام: edsbas.47AC32E5
قاعدة البيانات: BASE
الوصف
DOI:10.1007/s40747-024-01397-0