We use cookies to improve your experience with our site.

Indexed in:

SCIE, EI, Scopus, INSPEC, DBLP, CSCD, etc.

Submission System
(Author / Reviewer / Editor)
Advanced Search
Volume 20 Issue 6
November  2005
Turn off MathJax
Article Contents
Abstract
References
Related Articles
Hua Li, Shui-Cheng Yan, Li-Zhong Peng. Robust Non-Frontal Face Alignment with Edge Based Texture[J]. Journal of Computer Science and Technology, 2005, 20(6): 849-854.
Citation: Hua Li, Shui-Cheng Yan, Li-Zhong Peng. Robust Non-Frontal Face Alignment with Edge Based Texture[J]. Journal of Computer Science and Technology, 2005, 20(6): 849-854.
shu

Robust Non-Frontal Face Alignment with Edge Based Texture

  • 1 LMAM, School of Mathematical Sciences, Peking University, Beijing 100871, P.R. China2 Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong Special Administration Region, P.R. China

More Information
  • Received Date: May 13, 2004
  • Revised Date: March 31, 2005
  • Published Date: November 14, 2005
    Abstract
  • This paper proposes a new algorithm, called Edge-based Texture Driven Shape Model (E-TDSM), for non-frontal face alignment task. First, the texture is defined as the un-warped edge image contained in the shape rectangle; then, a Bayesian network is constructed to describe the relationship between the shape and texture models; finally, Expectation-Maximization (EM) approach is utilized to infer the optimal texture and position parameters from the observedshape and texture information. Compared with the traditional shape localization algorithms, E-TDSM has the following advantages: 1) the un-warped edge-based texture can better predict the shape and is more robust to the illumination and expression variation than the conventional warped gray-level based texture; 2) the presented Bayesiannetwork indicates the logic structure of the face alignment task; and 3) the mutually enhanced shape and texture observations are integrated to infer the optimal parameters of the proposed Bayesian network using EM approach. The extensive experiments on non-frontal face alignment task demonstrate the effectiveness and robustness of the proposed E-TDSM algorithm.
    • FullText(HTML)
    • References (13)
  • [1]
    Romdhani S, Blanz V, Vetter T. Face identification by fitting a 3D Morphable model using linear shape and texture error functions. In Proc. 7th European Conf. Computer Vision., Copenhagen, Denmark, May 27--June 2, 2002, pp.3--19.
    [2]
    Li Y, Gong S, Liddell H. Modeling faces dynamically across views and over time. In Proc. 8th IEEE Int. Conf. Computer Vision, Vancouver, Canada, July 9--12, 2001, pp.554--559.
    [3]
    Lanitis A, Taylor C J, Cootes T F. Automatic interpretation and coding of face images using flexible models. IEEE Trans. Pattern Analysis and Machine Intelligence, 1997, 19(7): 743--756.
    [4]
    Moghaddam B, Pentland A. Probabilistic visual learning for object representation. IEEE Trans. Pattern Analysis and Machine Intelligence, 1997, 19(7): 696--710.
    [5]
    Cootes T F, Taylor C J. Statistical models of appearance for computer vision. Technical Report, University of Manchester, 2001.
    [6]
    van Ginneken B, Frangi A F, Staal J J et al. A non-linear gray-level appearance model improves active shape model segmentation. In Proc. 5th IEEE Workshop on Mathematical Models in Biomedical Analysis, Kauai, Hawaii, USA, Dec. 9--10, 2001, pp.205--212.
    [7]
    Mitchell S C, Lelieveldt B, Geest R van der et al. Segmentation of cardiac MR images: An active appearance model approach. In Proc. Key to the Future, Leiden International Medical Students Congress, Nov. 26--27, Nederlanders, 1999, p.52.
    [8]
    Yan S C, Liu C, Li S Z et al. Texture-constrained active shape models. In Proc. 1st Int. Workshop on Generative-Model Based Vision in Conjunction with European Conf. Computer Vision 2002, Copenhagen, Denmark, June 2, 2002, pp.107--113.
    [9]
    Bilms J. A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. ICSI-TR-97-021, UC. Berkeley, Apr. 1998.
    [10]
    Jolliffe I T. Principal Component Analysis. Springer-Verlag, 1986.
    [11]
    Cootes T F, Edwards, Taylor C J. Active appearance models. In Proc. 5th European Conference on Computer Vision, Freiburg, Germany, June 2--6, 1998, 2: 484--498.
    [12]
    Kent J T, Mardia K V. Shape, procrustes tangent projections and bilateral symmetry. Biometrika, 2001, 88(2): 469--485.
    [13]
    Yan S C, Li M J, Zhang H J, Cheng Q S. Ranking prior likelihood distributions for Bayesian shape localization framework. In Proc. 9th IEEE International Conference on Computer Vision, Nice, France, Oct. 13--16, 2003, 1: 51--58.
    • Relative Articles

  • Related Articles

    [1]Jiao-Yun Yang, Jun-Da Wang, Yi-Fang Zhang, Wen-Juan Cheng, Lian Li. A Heuristic Sampling Method for Maintaining the Probability Distribution[J]. Journal of Computer Science and Technology, 2021, 36(4): 896-909. DOI: 10.1007/s11390-020-0065-6
    [2]Jun-Gang Xu, Yue Zhao, Jian Chen, Chao Han. A Structure Learning Algorithm for Bayesian Network Using Prior Knowledge[J]. Journal of Computer Science and Technology, 2015, 30(4): 713-724. DOI: 10.1007/s11390-015-1556-8
    [3]Concha Bielza, Juan A. Fern&aacutendez del Pozo, Pedro Larra&ntildeaga. Parameter Control of Genetic Algorithms by Learning and Simulation of Bayesian Networks —— A Case Study for the Optimal Ordering of Tables[J]. Journal of Computer Science and Technology, 2013, 28(4): 720-731. DOI: 10.1007/s11390-013-1370-0
    [4]Amin Nikanjam, Adel Rahmani. Exploiting Bivariate Dependencies to Speedup Structure Learning in Bayesian Optimization Algorithm[J]. Journal of Computer Science and Technology, 2012, 27(5): 1077-1090. DOI: 10.1007/s11390-012-1285-1
    [5]LIU WeiYi, SONG Ning. Fuzzy Functional Dependencies and Bayesian Networks[J]. Journal of Computer Science and Technology, 2003, 18(1).
    [6]HUANG YU, XU Guangyou, ZHU Yuanxin. Extraction of Spatial-Temporal Features for Vision-Based Gesture Recognition[J]. Journal of Computer Science and Technology, 2000, 15(1): 64-72.
    [7]Zhou Jingzhou. A Neural Network Model Based on Logical Operations[J]. Journal of Computer Science and Technology, 1998, 13(5): 464-470.
    [8]Hou Zhengfeng. A Topology Designing System for a Computer Network[J]. Journal of Computer Science and Technology, 1998, 13(1): 91-96.
    [9]Chen Bin, Hong Jiarong, Wang Yadong. The Minimum Feature Subset Selection Problem[J]. Journal of Computer Science and Technology, 1997, 12(2): 145-153.
    [10]Zhang Bo, Zhang Ling. The Complexity of Recognition in the Single-Layered PLN Network with Feedback Connections[J]. Journal of Computer Science and Technology, 1993, 8(4): 31-35.
    • Supplements (0)

Catalog

    Get Citation
    XML
    Article views (21) PDF downloads (1190) Cited by()
    Related

    Copyright ©2025 JCST, All Rights Reserved     京ICP备05002829号-1

    Institute of Computing Technology, Chinese Academy of Sciences
    P.O. Box 2704, Beijing 100190, P.R. China

    Tel.: 86-10-62610746 E-mail: jcst@ict.ac.cn

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return