A Benchmark and Comparative Study of Video-Based Face Recognition on COX Face Database
A Benchmark and Comparative Study of Video-Based Face Recognition on COX Face Database
复制标题
DOI：
10.1109/tip.2015.2493448
复制
发表时间：
2015-10
影响因子：
10.6
通讯作者：
Zhiwu Huang;S. Shan;Ruiping Wang;Haihong Zhang;S. Lao;Alifu Kuerban;Xilin Chen
中科院分区：
文献类型：
--
作者：
Zhiwu Huang;S. Shan;Ruiping Wang;Haihong Zhang;S. Lao;Alifu Kuerban;Xilin Chen
基于静止图像的人脸识别已经得到了广泛的研究，而基于视频的人脸识别研究相对不足，尤其是在基准数据集和比较方面。基于真实世界视频的人脸识别应用需要用于三种不同场景的技术：1）视频到静止（V2S）; 2）静止到视频（S2V）;以及3）视频到视频（V2V），分别将视频或静止图像作为查询或目标。据我们所知，很少有数据集和评估协议对所有三种情况进行基准测试。为了便于研究这个特定的主题，本文贡献了一个基准和比较研究的基础上，新收集的静态/视频人脸数据库，名为COX1人脸数据库。具体来说，我们做了三个贡献。首先，我们收集并发布了一个大规模的静态/视频人脸数据库，以模拟三种不同的基于视频的人脸识别场景（即，V2S、S2V和V2V）。其次，为基准测试我们的数据库上设计的三个场景，我们回顾和实验比较了一些现有的基于集合的方法。第三，我们进一步提出了一种新的点到集相关学习（PSCL）方法，并通过实验表明，它可以作为一个有前途的基线方法，在考克斯人脸数据库上的V2S/S2V人脸识别。大量的实验结果清楚地表明，基于视频的人脸识别需要更多的努力，我们的考克斯人脸数据库是一个很好的基准数据库的评估。
Face recognition with still face images has been widely studied, while the research on video-based face recognition is inadequate relatively, especially in terms of benchmark datasets and comparisons. Real-world video-based face recognition applications require techniques for three distinct scenarios: 1) Videoto-Still (V2S); 2) Still-to-Video (S2V); and 3) Video-to-Video (V2V), respectively, taking video or still image as query or target. To the best of our knowledge, few datasets and evaluation protocols have benchmarked for all the three scenarios. In order to facilitate the study of this specific topic, this paper contributes a benchmarking and comparative study based on a newly collected still/video face database, named COX1 Face DB. Specifically, we make three contributions. First, we collect and release a largescale still/video face database to simulate video surveillance with three different video-based face recognition scenarios (i.e., V2S, S2V, and V2V). Second, for benchmarking the three scenarios designed on our database, we review and experimentally compare a number of existing set-based methods. Third, we further propose a novel Point-to-Set Correlation Learning (PSCL) method, and experimentally show that it can be used as a promising baseline method for V2S/S2V face recognition on COX Face DB. Extensive experimental results clearly demonstrate that video-based face recognition needs more efforts, and our COX Face DB is a good benchmark database for evaluation.