一种多特征相结合的三维人脸关键点检测方法

冯超; 陈清江

doi:10.3788/YJYXS20183304.0306

您当前的位置：

首页 >

文章列表页 >

一种多特征相结合的三维人脸关键点检测方法

图像处理 | 更新时间：2020-07-06

- 一种多特征相结合的三维人脸关键点检测方法
- A key point detection method of 3 D face based on multi-feature
- 液晶与显示 2018年33卷第4期页码：306-316
- 作者机构：
  
  1.陕西能源职业技术学院资源与测绘工程学院, 陕西咸阳 712000
  2.西安建筑科技大学理学院, 陕西西安 710055
- 作者简介：
  
  [ "冯超(1986-), 男, 陕西周至人, 硕士, 讲师, 主要研究领域为矿业工程、遥感技术与图像处理。E-mail:546160401@qq.com" ]
  [ "陈清江(1966-), 男, 河南信阳人, 博士, 教授, 主要研究领域为计算数学、小波分析理论与图像处理。E-mail:280274242@qq.com" ]
- 基金信息：
  
  国家自然科学基金(61403298);陕西省自然科学基金(2015JM1024);National Nature Science Foundation of China(61403298);Natural Science Foundation of Shanxi Province of China(2015JM1024)
- DOI：10.3788/YJYXS20183304.0306
  中图分类号： TP391
- 收稿日期：2017-12-11，
  
  录用日期：2018-2-28，
  
  纸质出版日期：2018-04-05
- 稿件说明：
移动端阅览
冯超, 陈清江. 一种多特征相结合的三维人脸关键点检测方法[J]. 液晶与显示, 2018,33(4):306-316.

Chao FENG, Qing-jiang CHEN. A key point detection method of 3 D face based on multi-feature[J]. Chinese journal of liquid crystals and displays, 2018, 33(4): 306-316.
冯超, 陈清江. 一种多特征相结合的三维人脸关键点检测方法[J]. 液晶与显示, 2018,33(4):306-316. DOI： 10.3788/YJYXS20183304.0306.

Chao FENG, Qing-jiang CHEN. A key point detection method of 3 D face based on multi-feature[J]. Chinese journal of liquid crystals and displays, 2018, 33(4): 306-316. DOI： 10.3788/YJYXS20183304.0306.

摘要

关键点检测是三维人脸识别过程中非常重要的一步，为了提高关键点检测的准确度，提出了一种多特征相结合的三维人脸关键点检测方法。首先对训练集中的三维人脸手工标记关键点，计算三维人脸上每一点的不同特征值，得到每类关键点关于每个特征的均值和方差，其次对关键点和非关键点上的特征进行线性判别分析，得到与每个关键点相关的分值加权向量，将前面得到的均值，方差以及分值加权向量作为线下训练的结果输出。最后对于一个输入模型，结合线下训练的结果得到每个关键点的候选点，利用这些候选点构建人脸结构模型。再根据绝对距离约束，相对位置约束，FLM模型一致性分类，自旋图描述符等方法确定最终的关键点。实验部分，从CASIA-3D FaceV1和FRGC V2.0数据库中选不同姿态，不同表情，姿态与表情混合的三个数据集，对其进行关键点检测。实验结果表明，不同姿态的检测率为94.5%，不同表情的检测率为94%，和其他文献相比，检测率平均提高了20%，并且有着较高的运算效率。

Abstract

Key point detection plays an important role in the process of 3D face recognition. In order to improve the accuracy of key points detection

a new method of 3D face key points detection based on multi feature is proposed. Firstly

the key points of the 3d face of the training set are manually marked

and the different eigenvalues of each point of 3D face are calculated

and the mean and variance of each feature are obtained for each key point. Secondly

the linear discriminant analysis is carried out on the characteristics of key points and non-critical points

thus get the score-weighted vector associated with each key point. The mean

variance

and score-weighted vectors of the previous ones are the output of the offline training. Finally

for an input model

we can get the candidate points of each key point combined the results of offline training

and construct the face structure model using these candidate points. According to the absolute distance constraint

relative position constraint

FLM model consistency classification

spin map and other methods we can determine the final point. In the experimental part

we select the three data sets of different postures

different expressions

gestures and expressions mixed from CASIA-3D FaceV1 and FRGC V2.0 database to detect the key points. Experiment results show that the detection rate of different gestures was 94.5%

and the detection rate of different expressions was 94%. Compared with other literatures

the detection rate increases by 20% on average. In addition

the algorithm has higher computing efficiency.

关键词

Keywords

references

何春.人脸识别技术综述[J].智能计算机与应用, 2016, 6(5):112-114.

HE C. Survey of face recognition technology[J]. Intelligent Computer and Applications , 2016, 6(5):112-114. (in Chinese)

王晓华, 孙小姣.联合Gabor降维特征与奇异值特征的人脸识别[J].光学精密工程, 2015, 23(10):553-558.

WANG X H, SUN X J. Face recognition based on Gabor reduction dimensionality features and singular value decomposition features[J]. Optics and Precision Engineering , 2015, 23(10):553-558. (in Chinese)

刘明晶. 3D人脸识别中的支持向量机研究[D]. 沈阳: 东北大学, 2009.

LIU M J. Support vector machine in 3D face recognition[D]. Sheyang: Northeastern University, 2009. (in Chinese)

郭哲, 樊养余, 刘姝, 等.三维到二维:人脸本征形状描述图[J].光学精密工程, 2014, 22(12):3391-3400.

GUO Z, FAN Y Y, LIU S, et al . 3D to 2D:Facial intrinsic shape description maps[J]. Optics and Precision Engineering , 2014, 22(12):3391-3400. (in Chinese)

DRIRA H, BEN AMOR B, SRIVASTAVA A, et al . 3D face recognition under expressions, occlusions, and pose variations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013, 35(9):2270-2283.

XU C H, TAN T N, WANG Y H, et al . Combining local features for robust nose location in 3D facial data[J]. Pattern Recognition Letters , 2006, 27(13):1487-1494.

SEGUNDO M P, QUEIROLO C, BELLON O R P, et al . Automatic 3D facial segmentation and landmark detection[C]// Proceedings of the 14th International Conference on Image Analysis and Processing . Modena, Italy: IEEE, 2007: 431-436.

MIAN A, BENNAMOUN M, OWENS R. An efficient multimodal 2D-3D hybrid approach to automatic face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2007, 29(11):1927-1943.

刘瑶, 马杰, 赵季, 等.基于自旋图的三维自动目标识别[J].红外与激光工程, 2012, 41(2):543-548.

LIU Y, MA J, ZHAO J, et al . Three dimensional automatic target recognition based on spin-images[J]. Infrared and Laser Engineering , 2012, 41(2):543-548. (in Chinese)

PERAKIS P, PASSALIS G, THEOHARIS T, et al . 3D facial landmark detection under large yaw and expression variations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013, 35(7):1552-1564.

STEGMANN M B, GOMEZ D D. A brief introduction to statistical shape analysis[R]. Denmark: Technical University of Denmark, 2002.

COOTES T F, TAYLOR C J. Statistical models of appearance for computer vision[J]. Proceedings of SPIE-The International Society for Optical Engineering , 2000, 4322(1):236-248.

PERAKIS P, THEOHARIS T, PASSALIS G, et al . Automatic 3D facial region retrieval from multi-pose facial datasets[C]// Proceedings of the 2nd Eurographics Conference on 3D Object Retrieval . Munich, Germany: ACM, 2009: 37-44.

PERAKIS P, PASSALIS G, THEOHARIS T, et al . Partial matching of interpose 3D facial data for face recognition[C]// Proceedings of the 3rd International Conference on Biometrics: Theory, Applications, and Systems . Washington, DC, USA: IEEE, 2009: 1-8.

NAIR P, CAVALLARO A. 3-D face detection, landmark localization, and registration using a point distribution model[J]. IEEE Transactions on Multimedia , 2009, 11(4):611-623.

LU X G, JAIN A K. Multimodal facial feature extraction for automatic 3D face recognition[R]East Lansing, Michigan: Department of Computer Science, Michigar State University. 2005.

LU X G, JAIN A K. Automatic feature extraction for multiview 3D face recognition[C]// Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition . Southampton, UK: IEEE, 2006: 585-590.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进三维形状上下文的点云配准

自适应多尺度颜色特征目标跟踪算法研究

一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型

一种基于权重融合的JPEG隐写分析方法

基于MeanShift算法的航空影像联合分割