基于素描对视频的人脸识别研究

doi:10.13190/j.jbupt.2019-183

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (6): 170-176.doi: 10.13190/j.jbupt.2019-183

• 研究报告 • 上一篇

基于素描对视频的人脸识别研究

陈平¹, 皇甫大鹏¹, 王兴建^1,2, 党徳鹏²

1. 北京师范大学信息网络中心, 北京 100875;
2. 北京师范大学人工智能学院, 北京 100875

收稿日期:2019-07-24 出版日期:2019-12-28 发布日期:2019-11-15
作者简介:陈平(1974-),男,高级工程师,硕士生导师,E-mail:chenping@bnu.edu.cn.
基金资助:
国家自然科学基金项目（61370064，61274033，61271198）；赛尔网络下一代互联网技术创新项目（NGII20180603）

Sketch Based Face Recognition in Video

CHEN Ping¹, HUANGFU Da-peng¹, WANG Xing-jian^1,2, DANG De-peng²

1. Center of Information and Network Technology, Beijing Normal University, Beijing 100875, China;
2. School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China

Received:2019-07-24 Online:2019-12-28 Published:2019-11-15

摘要/Abstract

摘要： 在公共安全领域查找关键人，需在视频中比对素描进行检索.为此，改进了仅依靠对素描和视频数据中的人脸提取整体或者局部特征的识别算法，将人脸识别问题转为人脸检索问题，把这2种媒体数据表示为第3种数据，即图像列表.通过比较图像列表完成最终的特征比对.所设计的系统扩展了人脸识别的研究范围，且支持多种媒体数据的检索.对比人脸视频分析融合系统，对素描-视频数据进行人脸识别，结果显示，所提出算法的正确识别率和曲线下面积都有相应提高，而等错误率降幅显著.

关键词: 素描, 视频, 人脸识别

Abstract: For public securities, the sketch method is often need to be retrieved in video for seeking key people. An improved recognition algorithm that only extracts global or local features from sketch and video media data was presented. The problem of face recognition is turned into face retrieval. The above two medias data is represented as the so called third kind of data, i.e. image list and the final feature comparison is completed by comparing image list. The system designed here extends the research scope of face recognition and supports the retrieval of multi-media data. Compared with face recognition of face video analysis combined system for sketch-video data, the proposed design improves the correct recognition rate of precision and area under the curve, while the equal error rate of equal error rate decreases greatly.

Key words: sketch, video, face recognition

中图分类号:

TP391.4

陈平, 皇甫大鹏, 王兴建, 党徳鹏. 基于素描对视频的人脸识别研究[J]. 北京邮电大学学报, 2019, 42(6): 170-176.

CHEN Ping, HUANGFU Da-peng, WANG Xing-jian, DANG De-peng. Sketch Based Face Recognition in Video[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2019, 42(6): 170-176.

参考文献

[1] Klare Brendan, Zhifeng, Li A K, et al. Matching forensic sketches to mug shot photos[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3):639-646.
[2] Kiani Galoogahi H, Sim T. Face sketch recognition by local radon binary pattern:LRBP[C]//2012 19^th IEEE International Conference on Image Processing. New York:IEEE Press, 2012:355-359.
[3] Klare B, Jain A K. Sketch to photo matching:a feature-based approach[C]//Proceedings SPIE 7667, Biometric Technology for Human Identification VII. 2010(7667):766702.
[4] Liu J, Bae S, Park H, et al. Face photo-sketch recognition based on joint dictionary learning[C]//2015 14^th IAPR International Conference on Machine Vision Applications (MVA). Tokyo:IEEE Press, 2015:77-80.
[5] Zhang Y, McCullough C, Sullins J R, et al. Hand-drawn face sketch recognition by humans and a PCA-based algorithm for forensic applications[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A:Systems and Humans, 2010, 40(3):475-485.
[6] 龙伶敏. 基于Adaboost的人脸检测方法及眼睛定位算法研究[D]. 成都:电子科技大学, 2008:35.
[7] Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai:[s.n.], 2001:311-318.
[8] Viola Paul, Jones Michael. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2):137-154.
[9] Lienhart R, Maydt J. An extended set of Haar-like features for rapid object detection[C]//Proceedings of International Conference on Image Processing. New York:IEEE Press, 2002:I900-I903.
[10] Wu K L. Analysis of parameter selections for fuzzy cmeans[J]. Pattern Recognition, 2012, 45(1):407-415.
[11] Cognitec Systems GmbH. Face VACS-Video Scan[EB/OL]. 2019[2019-04-16]. https://www.cognitec.com/facevacs-videoscan.html.

[1]	张雅斓班晓娟董子瑞. 面向单目视频的非牛顿流体仿真重建[J]. 北京邮电大学学报, 2023, 46(2): 109-115.
[2]	张浩冯春燕杨佳汇郭彩丽周博文. 面向语义通信的3D骨骼点数据编码与压缩方法[J]. 北京邮电大学学报, 2022, 45(6): 62-69.
[3]	蒋林, 武鑫, 崔继兴, 谢晓燕, 山蕊. HEVC运动估计中SAD算法的动态可重构实现[J]. 北京邮电大学学报, 2018, 41(4): 37-43.
[4]	周东, 李昀峰, 高妍, 阮雅端, 陈启美. 融合区域纹理梯度的船舶阴影视频去除算法[J]. 北京邮电大学学报, 2017, 40(s1): 81-84,97.
[5]	杨名, 阮雅端, 陈林凯, 张鹏, 陈启美. 甚高速区域卷积神经网络的船舶视频检测方法[J]. 北京邮电大学学报, 2017, 40(s1): 130-134.
[6]	肖贺, 涂钦, 门爱东. 显著图联合改进的JND模型[J]. 北京邮电大学学报, 2017, 40(2): 79-83.
[7]	李亚, 王广润, 王青. 基于深度卷积神经网络的跨年龄人脸识别[J]. 北京邮电大学学报, 2017, 40(1): 84-88,110.
[8]	耿杨, 金家义, 孟洛明. 基于压缩编码和传输损伤的视频QoE评估方法[J]. 北京邮电大学学报, 2016, 39(s1): 55-58,71.
[9]	王小明, 朱腾蛟, 李鹏, 张立臣, 张丹. 机会网络中视频分块随机集中调度算法[J]. 北京邮电大学学报, 2016, 39(3): 75-79.
[10]	张珍珍, 侯建军, 李赵红, 郭胜. 基于MSSIM商一致性的视频插帧和删帧篡改检测[J]. 北京邮电大学学报, 2015, 38(4): 86-90.
[11]	刘杰平, 何越盛, 韦岗. 像素域基于广义高斯分布的WZ帧重构方案设计[J]. 北京邮电大学学报, 2015, 38(1): 103-107.
[12]	陈雷, 王晓湘. 减少反馈策略和联合编码策略下的多播资源分配[J]. 北京邮电大学学报, 2013, 36(1): 36-40.
[13]	常侃, 覃团发, 张文豪, 门爱东. 块级别自适应层间帧内预测方法[J]. 北京邮电大学学报, 2012, 35(6): 11-15.
[14]	何能强张学聃杜军任勇. 基于视频解码依赖性的低延时无线视频广播纠删编码[J]. 北京邮电大学学报, 2012, 35(4): 85-88.
[15]	谌志鹏邹建成. 基于对象的抗几何攻击的视频水印算法[J]. 北京邮电大学学报, 2012, 35(4): 33-37.

基于素描对视频的人脸识别研究

Sketch Based Face Recognition in Video

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价