Unconstrained Face Detection and Open-Set Face Recognition Challenge-猫眼课题宝

DOI：

10.1109/btas.2017.8272759

发表时间：

2017-08

期刊：

2017 IEEE International Joint Conference on Biometrics (IJCB)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Manuel Günther;Peiyun Hu;C. Herrmann;Chi-Ho Chan;Min Jiang;Shufan Yang;A. Dhamija;Deva Ramanan;J. Beyerer;J. Kittler;Mohamad Al Jazaery;Mohammad Iqbal Nouyed;G. Guo;Cezary Stankiewicz;T. Boult

人脸检测和识别基准已转向更困难的环境。本文提出的挑战解决了从室外监控摄像头自动检测和识别人员的下一步方向。虽然人脸检测在从网络收集的图像中取得了显着的成功，但监控摄像头包含更多样化的遮挡、姿势、天气条件和图像模糊。尽管人脸验证或闭集人脸识别在某些数据集上已经超越了人类的能力，但开放集识别要复杂得多，因为它需要拒绝未知身份和人脸检测器的错误接受。我们表明，不受约束的人脸检测可以达到较高的检测率，尽管错误接受率适中。相比之下，开放集人脸识别目前还很薄弱，需要更多的关注。

Face detection and recognition benchmarks have shifted toward more difficult environments. The challenge presented in this paper addresses the next step in the direction of automatic detection and identification of people from outdoor surveillance cameras. While face detection has shown remarkable success in images collected from the web, surveillance cameras include more diverse occlusions, poses, weather conditions and image blur. Although face verification or closed-set face identification have surpassed human capabilities on some datasets, open-set identification is much more complex as it needs to reject both unknown identities and false accepts from the face detector. We show that unconstrained face detection can approach high detection rates albeit with moderate false accept rates. By contrast, open-set face recognition is currently weak and requires much more attention.

Unconstrained Face Detection and Open-Set Face Recognition Challenge

文献摘要

被引文献

相似文献