利用场景光照识别优化的双目活体检测方法

PDF下载HTML

Title:

Binocular camera based face liveness detection with optimized scene illumination recognition

作者:

林峰¹, 杨忠程², 冯英², 颜水成², 魏子昆²

1. 贵阳市信捷科技有限公司, 贵州 贵阳 550081;
2. 上海依图网络科技有限公司, 上海 200051

Author(s):

LIN Feng¹, YANG Zhongcheng², FENG Ying², YAN Shuicheng², WEI Zikun²

1. Guiyang Xinjie Technology Co., Ltd., Guiyang 550081, China;
2. YITU Tech, Shanghai 200051, China

关键词:

人脸活体检测; 人脸防伪; 展示攻击检测; 身份识别; 生物识别安全; 深度学习; 卷积神经网络; PID控制

Keywords:

face liveness detection; face anti-counterfeiting; display attack detection; identity recognition; biometric security; deep learning; convolutional neural network; PID control

分类号:

TP391

DOI:

10.11992/tis.201912026

摘要:

人脸识别是生物特征识别技术中应用最广的技术之一。其中，能判断人脸图像是否是真实人脸的活体检测模块，是系统安全运行的重要保障。目前从安全度和经济性两方面综合考虑，最常用的活体检测方法是双目活体检测。但由于不同场景下光线亮度和角度变化很大，拍摄的人脸图片质量参差不齐，严重影响了活体检测的质量。针对这一问题，提出了通过对场景光照识别进行优化从而提升检测准确度的双目活体识别算法。算法通过串级PID算法对摄像头的感光度和补光灯进行控制，并利用人脸识别算法定位优化测光区域，从而对不同的光线强度和角度采取不同的策略。经过实验验证：本方法将活体检测在复杂场景下的准确率提升约30%，保证了算法在室内外不同光照场景下的有效性。

Abstract:

Face recognition is one of the most widely applied biometric identification technologies, in which face liveness detection aiming to determine whether a face is genuine or fake, is used to help face recognition systems defend against replay and print attacks, and thus ensure system security. Considering safety and economy, binocular camera based face liveness detection is most commonly adopted at present. However, due to significant variations in lighting conditions of different scenes as well as face poses, the captured face images are often of low quality, which greatly harms the performance of face liveness detection. In this paper, we propose a binocular camera based face liveness detection algorithm, which improves detection performance through optimizing scene illumination recognition. In particular, the proposed algorithm uses the cascaded PID algorithm to adjust the light sensitivity and light supplement of the camera subject to specific lighting and pose angles. It also modifies the photometric range to be within the face area in the case of backlight to ensure effectiveness of the light exposure and supplement control strategy. Extensive experiments have been conducted and the results show that the proposed model outperforms other methods by around 30% in accuracy in complex scenes, with ensured generalizability to diverse application scenes.