[1]王世昊,宋晓宁.基于动态多视角模型集成策略的人脸特征点定位算法[J].南京理工大学学报(自然科学版),2018,42(03):278.[doi:10.14177/j.cnki.32-1397n.2018.42.03.004]
 Wang Shihao,Song Xiaoning.Facial features localization algorithm based on integration strategy of dynamic multi-view models[J].Journal of Nanjing University of Science and Technology,2018,42(03):278.[doi:10.14177/j.cnki.32-1397n.2018.42.03.004]
点击复制

基于动态多视角模型集成策略的人脸特征点定位算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
42卷
期数:
2018年03期
页码:
278
栏目:
出版日期:
2018-06-30

文章信息/Info

Title:
Facial features localization algorithm based on integration strategy of dynamic multi-view models
文章编号:
1005-9830(2018)03-0278-08
作者:
王世昊宋晓宁
江南大学 物联网工程学院,江苏 无锡 214122
Author(s):
Wang ShihaoSong Xiaoning
School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China
关键词:
多视角模型 人脸特征点定位 级联回归模型 姿态分类算法
Keywords:
multi-view models facial features localization cascade regression model pose classification algorithm
分类号:
TP391
DOI:
10.14177/j.cnki.32-1397n.2018.42.03.004
摘要:
为提高在非限制环境下多种人脸姿态特征点定位的准确性,该文提出了1种新的人脸特征点定位算法。在基于级联回归的多视角模型的训练和测试过程中,使用姿态分类算法对不同的人脸样本进行分类。使用多视角模型集成策略预测特征点位置。实验证明,与显示形状回归(ESR)等算法比较,该文算法对非限制环境下人脸表观变化有更好的鲁棒性。
Abstract:
A new facial features localization algorithm is presented to improve the accuracy of various facial pose features localization in an unconstrained environment. Different face samples are classified by using pose classification algorithms during the training and testing process of multi-view models based on cascade regression. Facial key points are forecasted by using an integration strategy for various multi-view models. Experimental results show that,compared with the explicit shape regression(ESR),etc,this algorithm is more robust to changes in facial expression in an unconstrained environment.

参考文献/References:

[1] Cao Xudong,Wei Yichen,Wen Fang,et al. Face alignment by explicit shape regression[J]. International Journal of Computer Vision,2014,107(2):177-190.
[2]Cootes T F,Taylor C J,Cooper D H,et al. Active shape models—their training and application[J]. Computer Vision and Image Understanding,1995,61(1):38-59.
[3]Cootes T F,Edwards G J,Taylor C J. Active appearance models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):681-685.
[4]Dollár P,Welinder P,Perona P. Cascaded pose regression[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco,USA:IEEE,2010:1078-1085.
[5]Ren Shaoqing,Cao Xudong,Wei Yichen,et al. Face alignment at 3000 FPS via regressing local binary features[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington,DC,USA:IEEE Computer Society,2014:1685-1692.
[6]Zhu Shizhan,Li Cheng,Loy C C,et al. Face alignment by coarse-to-fine shape searching[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston,MA,USA:IEEE,2015:4998-5006.
[7]Zhu Shizhan,Li Cheng,Loy C C,et al. Unconstrained face alignment via cascaded compositional learning[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,NV,USA:IEEE,2016:3409-3417.
[8]王丽婷,丁晓青,方驰. 基于随机森林的人脸关键点精确定位方法[J]. 清华大学学报(自然科学版),2009,49(4):543-546.
Wang Liting,Ding Xiaoqing,Fang Chi. Accurate localization of facial feature points based on random forest classifier[J]. Journal of Tsinghua University(Science and Technology),2009,49(4):543-546.
[9]Burgos-Artizzu X P,Perona P,Dollár P. Robust face landmark estimation under occlusion[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington,DC,USA:IEEE Computer Society,2013:1513-1520.
[10]Chen Dong,Ren Shaoqing,Wei Yichen,et al. Joint cascade face detection and alignment[C]//13th European Conference on Computer Vision. Zurich,Switzerland:ECCV,2014:109-122.
[11]黄琛,丁晓青,方驰. 一种鲁棒高效的人脸特征点跟踪方法[J]. 自动化学报,2012,38(5):788-796.
Huang Chen,Ding Xiaoqing,Fang Chi. A robust and efficient facial feature tracking algorithm[J]. Acta Automatic Sinica,2012,38(5):788-796.
[12]Xiong Xuehan,De la Torre F. Supervised descent method and its applications to face alignment[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland,OR,USA:IEEE,2013:532-539.
[13]Ramanan D. Face detection,pose estimation,and landmark localization in the wild[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington,DC,USA:IEEE Computer Society,2012:2879-2886.
[14]Cristinacce D,Cootes T. Boosted regression active shape models[EB/OL]. http://www. dcs. warwick. ac. uk/bmvc2007/proceedings/CD-ROM/papers/131/bmvc2007_pap_final. pdf,2018-03-27.
[15]Ozuysal M,Fua P,Lepetit V. Fast keypoint recognition in ten lines of code[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis,MN,USA:IEEE,2007:1-8.
[16]Dollar P,Welinder P,Perona P. Cascaded pose regression[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco,CA,USA:IEEE,2010:1078-1085.
[17]Cˇech J,Franc V,UArˇiAcˇáArˇ M,et al. Multi-view facial landmark detection by using a 3D shape model[J]. Image & Vision Computing,2016,47(C):60-70.
[18]Deng Jiankang,Liu Qingshan,Yang Jing,et al. M3 CSR:Multi-view,multi-scale and multi-component cascade shape regression[J]. Image and Vision Computing,2016,47:19-26.
[19]Fan Haoqiang,Zhou Erjin. Approaching human level facial landmark localization by deep learning[J]. Image and Vision Computing,2016,47(C):27-35.
[20]Martinez B,Valstar M F. L2,1-based regression and prediction accumulation across views for robust facial landmark detection[J]. Image and Vision Computing,2016,47(C):36-44.
[21]UArˇiAcˇáArˇ M,Franc V,Thomas D,et al. Multi-view facial landmark detector learned by the structured output SVM[J]. Image and Vision Computing,2016,47:45-59.
[22]Milborrow S,Bishop T E,Nicolls F. Multiview active shape models with sift descriptors for the 300-W face landmark challenge[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Portland,Oregon,USA:IEEE,2013:378-385.
[23]Jaiswal S,Almaev T R,Valstar M F. Guided unsupervised learning of mode specific models for facial point detection in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Sydney,NSW,Australia:IEEE,2013:370-377.
[24]Baltrusaitis S,Robinson P,Morency L P. Constrained local neural fields for robust facial landmark detection in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Sydney,NSW,Australia:IEEE,2013:354-361.
[25]Zhou Erjin. Extensive facial landmark localization with coarse-to-fine convolutional network cascade[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Sydney,NSW,Australia:IEEE,2013:386-391.
[26]Hasan M K,Pal C,Moalem S. Localizing facial keypoints with global descriptor search,neighbour alignment and locally linear models[C]//IEEE International Conference on Computer Vision Workshops. Columbus,Ohio,USA:IEEE,2014:362-369.
[27]Feng Zhenhua,Kittler J,Christmas W,et al. Dynamic attention-controlled cascaded shape regression exploiting training data augmentation and fuzzy-set sample weighting[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,Hawaii,USA:IEEE Computer Society,2017:3681-3690.
[28]Feng Zhenhua,Huber P,Kittler J,et al. Random cascaded-regression copse for robust facial landmark detection[J]. IEEE Signal Processing Letters,2015,22(1):76-80.
[29]Feng Zhenhua,Hu Guosheng,Kittler J,et al. Cascaded collaborative regression for robust facial landmark detection trained using a mixture of synthetic and real images with dynamic weighting[J]. IEEE Transactions on Image Processing,2015,24(11):3425-3440.
[30]杨静宇,金忠. 人脸图像有效鉴别特征抽取与识别[J]. 南京理工大学学报,2000,24(3):193-198.
Yang Jingyu,Jin Zhong. Efficient discriminant feature extraction and recognition of face images[J]. Jouranl of Nanjing University of Science and Technology,2000,24(3):193-198.
[31]300 faces in-the-wild challenge(300-W),ICCV 2013[EB/OL]. https://ibug.doc.ic.ac.uk/resources/300-W/,2018-03-27.

备注/Memo

备注/Memo:
收稿日期:2017-08-14 修回日期:2017-09-30
基金项目:国家重点研发计划(2017YFC1601800); 中国博士后科学基金(2018T110441); 江苏省自然科学基金(BK20161135); 江苏省“六大人才高峰”高层次人才项目(XYDXX-012)
作者简介:王世昊(1992-),男,硕士生,主要研究方向:模式识别、人脸特征点识别,E-mail:15763268112@qq.com; 通讯作者:宋晓宁(1975-),男,副教授,主要研究方向:模式识别、高维图像处理和计算机视觉,E-mail:x.song@jiangnan.edu.cn。
引文格式:王世昊,宋晓宁. 基于动态多视角模型集成策略的人脸特征点定位算法[J]. 南京理工大学学报,2018,42(3):278-285.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2018-06-30