Tiny-FASNet: A Tiny Face Anti-spoofing Method Based on Tiny Module

doi:10.1007/978-3-030-88010-1_30

	Tiny-FASNet: A Tiny Face Anti-spoofing Method Based on Tiny Module
	Li, Ce1 ; Chang, Enbing 1; Liu, Fenghua 1; Xuan, Shuxing 1; Zhang, Jie1 ; Wang, Tian 2
	2021
会议名称	4th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)
会议录名称	PATTERN RECOGNITION AND COMPUTER VISION,, PT III
卷号	13021
页码	362-373
会议日期	DEC 19-21, 2021
会议地点	Univ Sci & Technol Beijing, Zhuhai, PEOPLES R CHINA
会议录编者/会议主办者	China Soc Image & Graph,Chinese Assoc Artificial Intelligence,China Comp Federat,Chinese Assoc Automat,Jiaotong Univ,Beijing Univ Posts & Telecommunicat
出版者	SPRINGER INTERNATIONAL PUBLISHING AG
摘要	Face Anti-spoofing (FAS) has arisen as one of the essential issues in face recognition systems. The existing deep learning FAS methods have achieved outstanding performance, but most of them are too complex to be deployed in embedded devices. Therefore, a tiny single modality FAS method (Tiny-FASNet) is proposed. First, to reduce the complexity, the tiny module is presented to simulate fully convolution operations. Specifically, some intrinsic features extracted by convolution are used to generate more features through cheap linear transformations. Besides, a simplified streaming module is proposed to keep more spatial structure information for FAS task. All models are trained and tested on depth images. The proposed model achieves 0.0034(ACER), 0.9990(TPR@FPR = 10E-2), and 0.9860(TPR@FPR = 10E-3) on CASIA-SURF dataset only with 0.018M parameters and 12.25M FLOPS. Extensive evaluations in two publicly available datasets (CASIA-SURF and CASIA-SURF CeFA) demonstrate the effectiveness of the proposed approach.
关键词	Face Anti-spoofing Tiny models Depth image
DOI	10.1007/978-3-030-88010-1_30
收录类别	CPCI-S
语种	英语
WOS研究方向	Computer Science ; Imaging Science & Photographic Technology
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Imaging Science & Photographic Technology
WOS记录号	WOS:000846861800030
ISSN	0302-9743
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/159877
专题	电气工程与信息工程学院机电工程学院
通讯作者	Li, Ce
作者单位	1.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Peoples R China; 2.Beihang Univ, Inst Artificial Intelligence, Beijing 100191, Peoples R China
第一作者单位	电气工程与信息工程学院
通讯作者单位	电气工程与信息工程学院
推荐引用方式 GB/T 7714	Li, Ce,Chang, Enbing,Liu, Fenghua,et al. Tiny-FASNet: A Tiny Face Anti-spoofing Method Based on Tiny Module[C]//China Soc Image & Graph,Chinese Assoc Artificial Intelligence,China Comp Federat,Chinese Assoc Automat,Jiaotong Univ,Beijing Univ Posts & Telecommunicat:SPRINGER INTERNATIONAL PUBLISHING AG,2021:362-373.