计算机科学 ›› 2019, Vol. 46 ›› Issue (9): 250-253.doi: 10.11896/j.issn.1002-137X.2019.09.037

所属专题: 人脸识别

• 图形图像与模式识别 • 上一篇    下一篇

非限定条件下无约束的多姿态人脸关键特征自动识别算法

赵志伟, 倪桂强   

  1. (陆军工程大学指挥控制工程学院 南京210007)
  • 收稿日期:2018-08-31 出版日期:2019-09-15 发布日期:2019-09-02
  • 通讯作者: 倪桂强(1966-),男,博士,教授,主要研究方向为网络管理、计算机图形学,E-mail:290604464@qq.com
  • 作者简介:赵志伟(1982-),男,博士生,主要研究方向为计算机视觉、深度学习;
  • 基金资助:
    863项目(2012AA01A509),中国高校科技期刊研究会基金(GBJXB1110)

Automatic Recognition Algorithm for Unconstrained Multi-pose Face Key Features under Unqualified Conditions

ZHAO Zhi-wei, NI Gui-qiang   

  1. (Institute of Command and Control Engineering,Army Engineering University,Nanjing 210007,China)
  • Received:2018-08-31 Online:2019-09-15 Published:2019-09-02

摘要: 多姿态人脸关键特征的自动识别,对处理人脸数据库中的图像具有重要意义。为了保证人脸关键特征被准确识别,需要对人脸关键特征进行提取。传统算法对多姿态人脸关键特征进行自动识别时有效性差、识别率低、效率低。为此,文中提出了一种基于向量机的多姿态人脸关键特征自动识别算法,利用相机的焦距将人脸关键特征图像的三维坐标表示出来,计算出多姿态人脸关键特征的三维信息。利用滤波器处理多姿态人脸的关键特征并对其进行提取,最后根据向量机的权值,对人脸关键特征的目标函数和特征中的噪声进行分析,计算人脸自动识别的条件概率和迭代次数,实现非限定条件下无约束多姿态人脸关键特征的自动识别。实验结果表明,所提算法能够对多姿态人脸关键特征进行自动识别,并且具有较高的识别率。

关键词: 非限定条件, 人脸关键特征, 无约束多姿态, 自动识别

Abstract: Automatic recognition of multi-pose faces key features is of great significance to the processing of images in face database.In order to ensure that face key features are accurately recognized,it is necessary to extract key features of the face.When the traditional algorithm is used to automatically recognize multi-pose face key features,the obtained face images are of poor efficiency,low recognition rate and low efficiency.This paper presented an automatic multi-pose face feature recognition algorithm based on vector machine.The 3D coordinate of the face key feature image is represented by the focal length of the camera,and the 3D information of the multi-pose face key feature is calculated.Filter is used to deal with multi-pose face key features.Finally,according to the weight of the vector machine,this paper analyzed the target function and the noise of face key features,calculated the condition probability and the iteration number of the face automatic recognition,and realized the automatic recognition of the key features of unconstrained multi-pose face under the unqualified condition.Experiment results show that the proposed algorithm can be used to automatically identifiy the multi-pose face key features,and has high recognition rate and recognition efficiency.

Key words: Automatic identification, Face key feature, Unconstrained multi-pose, Unqualified conditions

中图分类号: 

  • TP391.41
[1]LONG H Q,TAN T Z.Based on the Depth of Theconvolution Network and Local Binary Pattern of Face Recognition[J].Computer Simulation,2017,34(1):322-325.(in Chinese)龙海强,谭台哲.基于深度卷积网络算法的人脸识别方法研究[J].计算机仿真,2017,34(1):322-325.
[2]LI Q Y,JIANG J G,QI M B.Face Recognition Algorithm Based on Improved Deep Networks[J].Acta Electronica Sinica,2017,45(3):619-625.(in Chinese)李倩玉,蒋建国,齐美彬.基于改进深层网络的人脸识别算法[J].电子学报,2017,45(3):619-625.
[3]ZHANG J M,LIU Y C,WU H L,et al.A face recognition algorithm based on Gabor feature and projective dictionary pair learning[J].Computer Engineering and Science,2016,38(3):542-548.(in Chinese)张建明,刘阳春,吴宏林,等.基于Gabor特征与投影字典对学习的人脸识别算法[J].计算机工程与科学,2016,38(3):542-548.
[4]SHOU Z Y,YANG X F,LI M Y.Face recognition based on local feature and kernel low-rank representation[J].Application of Electronic Technique,2016,42(9):126-128.(in Chinese)首照宇,杨晓帆,李萌芽.基于局部特征与核低秩表示的人脸识别算法[J].电子技术应用,2016,42(9):126-128.
[5]WANG R.Based on the research of Adaboost face recognition algorithm[J].Electronic Design Engineering,2017,25(16):190-193.(in Chinese)王冉.基于Android平台人脸识别算法的应用[J].电子设计工程,2017,25(16):190-193.
[6]LI M,CAO L.The Face Sketch Synthesis Based on Sub-blocks LBP and Optimization[J].Bulletin of Science and Technology,2017,33(8):170-174.(in Chinese)李猛,曹林.基于子块LBP和最优相关的素描人脸合成[J].科技通报,2017,33(8):170-174.
[7]XIE W D.Research on Intelligent Recognition and Improvement of Facial Expression in Cloud Computing Environment[J].Computer Measurement & Control,2017,25(5):162-164.(in Chinese)谢文达.云计算环境下人脸表情智能识别改进技术研究[J].计算机测量与控制,2017,25(5):162-164.
[8]FENG Y P,AN X M.Subspace Face Recognition AlgorithmFused with Speed-up Robust Features[J].Science Technology and Engineering,2017,17(6):220-225.(in Chinese)冯宇平,安雪美.融合加速稳健特征的子空间人脸识别方法[J].科学技术与工程,2017,17(6):220-225.
[9]WANG X H,ZHAO Z X.PCA face recognition algorithm combined with gamma transform and wavelet transform[J].Computer Engineering and Applications,2016,52(5):190-193.(in Chinese)王晓华,赵志雄.结合伽马变换和小波变换的PCA人脸识别算法[J].计算机工程与应用,2016,52(5):190-193.
[10]ZHAO Z G,JU Z,GU H.Research on Low Resolution Face Recognition with Pose Variations[J].Control Engineering of China,2016,23(7):1057-1062.(in Chinese)赵志国,鞠哲,顾宏.低分辨率多姿态人脸识别算法研究[J].控制工程,2016,23(7):1057-1062.
[11]ABDALMAGEED W,WU Y,NEVATIA R,et al.Face recognition using deep multi-pose representations[C]//2016 IEEE Winter Conference on Applications of Computer Vision.IEEE,2016:1-9.
[12]SEO J J,KIM H I,YONG M R.Pose-Robust and Discriminative Feature Representation by Multi-task Deep Learning for Multi-view Face Recognition[C]//IEEE International Symposium on Multimedia.IEEE,2016:166-171.
[13]YANG J.Multi-pose Face Recognition Algorithm Based onSparse Representation[C]//International Conference on Intelligent Transportation,Big Data & Smart City.IEEE Computer Society,2016:113-116.
[14]YANG Z B,HOU L Y,YANG D L.Improved face recognition algorithm of attitude correction[J].Microcomputer & its Applications,2016,35(3):56-60.(in Chinese)杨作宝,侯凌燕,杨大利.改进的多姿态矫正的人脸识别算法[J].微型机与应用,2016,35(3):56-60.
[15]WU K,ZHU H L,HAO Y Y,et al.Cascade regression based multi-pose face alignment[J].Journal of Image and Graphics,2017,22(2):257-264.(in Chinese)伍凯,朱恒亮,郝阳阳,等.级联回归的多姿态人脸配准[J].中国图象图形学报,2017,22(2):257-264.
[16]LIAO H,LU S,WANG D.Tied factor analysis for uncon-strained face pose classification[J].Optik-International Journal for Light and Electron Optics,2016,127(23):11553-11566.
[17]JONATHON PHILLIPS P,MOON H,RIZVI S A,et al.The Feret evaluation methodology for face recognition algorithms[J].IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(10):1090-1104.MA H,SUN W C,SHI J H,et al.A Low-Resolution of Face Recognition Method Based on Curvelet Transform [J].Journal of Chongqing University of Technology(Natural Science),2018,32(11):168-174.(in Chinese)马慧,孙万春,史君华,等.基于Curvelet变换的低分辨率人脸识别方法[J].重庆理工大学学报(自然科学),2018,32(11):168-174.ZHU Z G, HE M X.Gender discriminant model of face based on local feature and depth neural network[J]. Machine Tool & Hydraulics,2018,46(6):127-132,151.(in Chinese)朱正国,何明星.基于局部特征和深度神经网络的人脸性别判别模型研究[J].机床与液压,2018,46(6):127-132,151.
[1] 郁舒昊, 周辉, 叶春杨, 王太正.
SDFA:基于多特征融合的船舶轨迹聚类方法研究
SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion
计算机科学, 2022, 49(6A): 256-260. https://doi.org/10.11896/jsjkx.211100253
[2] 杨进才, 胡巧玲, 胡泉.
基于规则的有标复句关系的自动识别
Rule-based Automatic Recognition of Relations for Marked Complex Sentences
计算机科学, 2021, 48(11A): 124-129. https://doi.org/10.11896/jsjkx.210100226
[3] 游兰, 韩雪薇, 何正伟, 肖丝雨, 何渡, 潘筱萌.
基于改进Seq2Seq的短时AIS轨迹序列预测模型
Improved Sequence-to-Sequence Model for Short-term Vessel Trajectory Prediction Using AIS Data Streams
计算机科学, 2020, 47(9): 169-174. https://doi.org/10.11896/jsjkx.190800060
[4] 王鹏, 苏伟, 张久文, 刘映杰, 王臻睿.
基于船舶自动识别系统与人工神经网络的船舶载重预测
Prediction of Vessel Load Based on Vessel Automatic Identification System and Artificial Neural Network
计算机科学, 2020, 47(6A): 49-53. https://doi.org/10.11896/JsJkx.191000074
[5] 陈晋音, 成凯回, 郑海斌.
低信噪比下基于深度学习的调制模式识别方法
Deep Learning Based Modulation Recognition Method in Low SNR
计算机科学, 2020, 47(6A): 283-288. https://doi.org/10.11896/JsJkx.190800072
[6] 权波, 杨博辰, 胡可奇, 郭晨萱, 李巧勤.
基于LSTM的船舶航迹预测模型
Prediction Model of Ship Trajectory Based on LSTM
计算机科学, 2018, 45(11A): 126-131.
[7] 徐凯,邱家瑜,李燕.
一种加入时间维的船舶轨迹高效离线压缩算法研究
Offline Efficient Compression Algorithm for AIS Data Retains Time Elapsing Dimension
计算机科学, 2017, 44(Z11): 498-502. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.106
[8] 贾春雪,罗琦,龚杨杨.
不规则障碍物的避障路径规划
Obstacle Avoidance Path Planning for Irregular Obstacles
计算机科学, 2017, 44(9): 290-295. https://doi.org/10.11896/j.issn.1002-137X.2017.09.054
[9] 孙伟豹 孙虎 王军.
判决法对数字和模拟信号的自动识别及验证
Automatic Recognition of Digital and Analog Communication Signals Based on Decision Laws
计算机科学, 2012, 39(Z11): 88-89.
[10] 曹晟,聂旭云,陈峥.
基于伪双目立体成像自动识别新技术
New Auto Identification Technology on Paper Currency Using Pseudo Binocular Stereo Imaging
计算机科学, 2012, 39(1): 19-22.
[11] 王上飞 薛佳 王煦法.
基于事例的面部动作单元识别算法

计算机科学, 2006, 33(11): 195-199.
[12] 吴爱燕 魏世泽.
一种基于网络的大型指纹数据库检索方法

计算机科学, 2005, 32(8): 196-199.
[13] 戴帅湘 周昌乐 黄孝喜 杨芸 王雪梅.
隐喻计算模型及其在隐喻分类上的应用

计算机科学, 2005, 32(5): 159-163.
[14] 樊闻斌 丁艳 潘金贵.
基于Ontology的网页关系识别研究

计算机科学, 2005, 32(11): 46-49.
[15] 崔国勤 李锦涛 高文 焦锋.
基于支持向量机的人脸识别方法

计算机科学, 2003, 30(4): 11-15.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!