不确定性估计结合主动外观模型三维特征提取的人脸识别方法

doi:10.11772/j.issn.1001-9081.2016.07.1971

计算机应用 ›› 2016, Vol. 36 ›› Issue (7): 1971-1975.DOI: 10.11772/j.issn.1001-9081.2016.07.1971

不确定性估计结合主动外观模型三维特征提取的人脸识别方法

卜宇¹, 任晓芳¹, 唐学军¹, 孙挺²

1. 新疆工程学院计算机工程系, 乌鲁木齐 830052;
2. 西北大学可视化研究所, 西安 710069

收稿日期:2016-01-04 修回日期:2016-03-20 出版日期:2016-07-10 发布日期:2016-07-14
通讯作者: 卜宇
作者简介:卜宇(1981-),女,新疆昌吉人,讲师,硕士,主要研究方向:图像处理、模式识别;任晓芳(1979-),女,河南商丘人,讲师,硕士,主要研究方向:图像处理、机器学习;唐学军(1969-),女,湖南邵阳人,高级实验师,主要研究方向:图像处理、机器学习;孙挺(1972-),男,河南沈丘人,副教授,博士研究生,主要研究方向:图像处理、科学可视化。
基金资助:
国家973计划前期研究专项（2011CB311802）。

Face recognition method based on uncertainty measurement combined with 3D features extraction using active appearance model

BU Yu¹, REN Xiaofang¹, TANG Xuejun¹, SUN Ting²

1. Department of Computer Engineering, Xinjiang Institute of Engineering, Urumqi Xinjiang 830052, China;
2. Institute of Visualization, Northwestern University, Xi'an Shaanxi 710069, China

Received:2016-01-04 Revised:2016-03-20 Online:2016-07-10 Published:2016-07-14
Supported by:
This work is partially supported by the Preliminary Research Project in National Basic Research Program (973 Program) of China (2011CB311802).

摘要/Abstract

摘要： 对于人脸识别分类结果中的可信度问题，提出一种基于不确定性理论的人脸识别方法。首先，为了估计3D特征，使用主动外观模型（AAM）和三角测量处理两幅未知对象的2D图像；然后，估计数据库中每个对象的分数，通过不确定性进一步处理两幅图像；最后，决策过程根据估计的分数和估计的不确定性分类列表，其中分类列表中存储了所有已识别对象及其对应的可信度。实验采用含两个摄像头的立体视觉系统采集各种姿态的人脸图像。与类似的概率预测测量方法相比，所提方法的正确检测率提高10%左右，漏检率至少降低了9%。实验结果表明，所提方法通过构建3D图像特征的不确定性信息和采用合适的统计方法提高了分类结果的准确率。

关键词: 人脸识别, 可信度, 不确定性, 生物识别算法, 分类器

Abstract: Concerning the credibility problem of the classification results in face recognition, a face recognition method based on the theory of uncertainty was proposed. Firstly, in order to estimate 3D features, Active Appearance Model (AAM) and triangulation were used to process two 2D images of unknown object. Then, the score of each object in the database was estimated, and two images were further processed through uncertainty. Finally, the decision was made based on the estimated scores and the estimated uncertainty classification list. All identified objects and their corresponding credibilities were stored in the classification list. Stereo vision system with two cameras captures face images of various postures in the experiment. Compared with a similar probability forecasting measurement method, the correct detection rate of the proposed method was increased by 10%, and the false detection rate was reduced by at least 9%. The experimental results show that the classification accuracy is improved by constructing the uncertainty information of 3D image feature and adopting appropriate statistical method.

Key words: face recognition, credibility, uncertainty, biological recognition algorithm, classifier

中图分类号:

TP391.413

卜宇, 任晓芳, 唐学军, 孙挺. 不确定性估计结合主动外观模型三维特征提取的人脸识别方法[J]. 计算机应用, 2016, 36(7): 1971-1975.

BU Yu, REN Xiaofang, TANG Xuejun, SUN Ting. Face recognition method based on uncertainty measurement combined with 3D features extraction using active appearance model[J]. Journal of Computer Applications, 2016, 36(7): 1971-1975.

参考文献

[1] RAJU A S, UDAYASHANKARA V. Biometric person authentication:a review[C]//Proceedings of the 2014 International Conference on Contemporary Computing and Informatics. Piscataway, NJ:IEEE, 2014:575-580.
[2] 邓剑勋,熊忠阳,曾代敏.基于EMD的融合特征快速多示例人脸识别算法[J].四川大学学报(工程科学版),2012,44(2):99-104.(DENG J X, XIONG Z Y, ZENG D M. Face recognition based on improved fast EMD-MIL framework and information fusion[J]. Journal of Sichuan University (Engineering Science Edition), 2012, 44(2):99-104.)
[3] 张祥德,张大为,唐青松,等.仿生算法与主成分分析相融合的人脸识别方法[J].东北大学学报:自然科学版,2009,30(7):972-975.(ZHANG X D, ZHANG D W, TANG Q S, et al. Face recognition algorithm integrating bionic algorithm with principal component analysis[J]. Journal of Northeastern University (Natural Science), 2009, 30(7):972-975.)
[4] 曹洁,吴迪,李伟.基于鉴别能力分析和LDA-LPP算法的人脸识别[J].吉林大学学报(工学版),2012,42(6):1527-1531.(CAO J, WU D, LI W. Face recognition based on discrimination power analysis and LDA-LPP algorithm[J]. Journal of Jilin University (Engineering and Technology Edition), 2012, 42(6):1527-1531.)
[5] 柴智,刘正光.应用复小波和独立成分分析的人脸识别[J].计算机应用,2010,30(7):1863-1866.(CHAI Z, LIU Z G. Face recognition using complex wavelet and independent component analysis[J]. Journal of Computer Applications, 2010, 30(7):1863-1866.)
[6] 严慧,金忠,杨静宇.非负二维主成分分析及在人脸识别中的应用[J].模式识别与人工智能,2009,22(6):809-814.(YAN H, JIN Z, YANG J Y. Non-negative two-dimensional principal component analysis and its application to face recognition[J]. Pattern Recognition and Artificial Intelligence, 2009, 22(6):809-814.)
[7] ZHANG D, WANG Q G, YU L, et al. Fuzzy-model-based fault detection for a class of nonlinear systems with networked measurements[J]. IEEE Transactions on Instrumentation & Measurement, 2013, 62(12):3148-3159.
[8] BETTA G, CAPRIGLIONE D, CORVINO M, et al. Face based recognition algorithms:a first step toward a metrological characterization[J]. IEEE Transactions on Instrumentation & Measurement, 2013, 62(5):1008-1016.
[9] 孔英会,张少明.多级FFD配准视频人脸超分辨率重建[J].光电工程,2012,39(10):46-53.(KONG Y H, ZHANG S M. Video Face super-resolution reconstruction based on multi-level FFD registration[J]. Opto-Electronic Engineering, 2012, 39(10):46-53.)
[10] WIJAYA I G P S, UCHIMURA K, KOUTAKI G. Multi-pose face recognition using fusion of scale invariant features[C]//Proceedings of the 20112nd International Congress on Computer Applications and Computational Science. Berlin:Springer, 2012:207-213.
[11] 张淑军,王高峰,石峰.基于AAM提取几何特征的人脸识别算法[J].系统仿真学报,2013,25(10):126-131.(ZHANG S J, WANG G F, SHI F. Face recognition algorithm based on geometric characteristics extracted by AAM[J]. Journal of System Simulation, 2013, 25(10):126-131.)
[12] ZHOU Y H, ZHENG D W, LIAO X H. Wavelet analysis of interannual LOD, AAM, and ENSO:1997-98 El Niño and 1998-99 La Niña signals[J]. Journal of Geodesy, 2001, 75(2/3):164-168.
[13] 李姗姗.基于PCA的实时人脸识别系统的设计与实现[D].北京:北京邮电大学,2012.(LI S S. Design and implementation of real time face recognition system based on PCA[D]. Beijing:Beijing University of Posts and Telecommunications, 2012.)
[14] JESPER K. The Guide to expression of uncertainty in measurement approach for estimating uncertainty:an appraisal[J]. Clinical Chemistry, 2003, 49(11):1822-1829.
[15] EMAMBAKHSH M, GAO J, EVANS A. Noise modelling for denoising and three-dimensional face recognition algorithms performance evaluation[J]. IET Computer Vision, 2015, 9(5):741-749.

不确定性估计结合主动外观模型三维特征提取的人脸识别方法

Face recognition method based on uncertainty measurement combined with 3D features extraction using active appearance model

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

[1]	高工, 杨红雨, 刘洪. 基于深度学习的三维点云人脸识别[J]. 计算机应用, 2021, 41(9): 2736-2740.
[2]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[3]	严爱军, 魏志远. 案例推理分类器的权重分配及案例库维护方法[J]. 计算机应用, 2021, 41(4): 1071-1077.
[4]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[5]	闫钧华, 侯平, 张寅, 吕向阳, 马越, 王高飞. 基于多尺度多分类器卷积神经网络的混合失真类型判定方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3178-3184.
[6]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[7]	方书雅, 刘守印. 基于学生人体检测的无感知课堂考勤方法[J]. 计算机应用, 2020, 40(9): 2519-2524.
[8]	赵青, 余元辉. 基于分层特征化网络的三维人脸识别[J]. 计算机应用, 2020, 40(9): 2514-2518.
[9]	尹春勇, 朱宇航. 基于垂直集成Tri-training的虚假评论检测模型[J]. 计算机应用, 2020, 40(8): 2194-2201.
[10]	肖跃雷, 张云娇. 基于特征选择和超参数优化的恐怖袭击组织预测方法[J]. 计算机应用, 2020, 40(8): 2262-2267.
[11]	王留洋, 俞扬信, 陈伯伦, 章慧. 基于共识和分类改善文档聚类的识别信息方法[J]. 计算机应用, 2020, 40(4): 1069-1073.
[12]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[13]	龚锐, 丁胜, 章超华, 苏浩. 基于深度学习的轻量级和多姿态人脸识别方法[J]. 计算机应用, 2020, 40(3): 704-709.
[14]	陈放, 刘晓瑞, 杨明业. 基于活体检测和身份认证的人脸识别安防系统[J]. 计算机应用, 2020, 40(12): 3666-3672.
[15]	邓天民, 方芳, 周臻浩. 基于改进空间金字塔池化卷积神经网络的交通标志识别[J]. 计算机应用, 2020, 40(10): 2872-2880.