|Table of Contents|

[1] He Lianghua, Zou Cairong, Zhao Li, et al. Optimal shape space and searching in the active shape model [J]. Journal of Southeast University (English Edition), 2005, 21 (3): 263-267. [doi:10.3969/j.issn.1003-7985.2005.03.004]
Copy

Optimal shape space and searching in the active shape model()
动态形状模型中最优搜索空间和最优搜索过程
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
21
Issue:
2005 3
Page:
263-267
Research Field:
Computer Science and Engineering
Publishing date:
2005-09-30

Info

Title:
Optimal shape space and searching in the active shape model
动态形状模型中最优搜索空间和最优搜索过程
Author(s):
He Lianghua1;  2;  Zou Cairong2;  Zhao Li2;  Hu Die2
1 Research Center of Learning Science, Southeast University, Nanjing 210096, China
2 Department of Radio Engineering, Southeast University, Nanjing 210096, China
何良华1;  2;  邹采荣2;  赵力2;  胡蝶2
1东南大学学习科学研究中心, 南京 210096; 2东南大学无线电工程系, 南京 210096
Keywords:
active shape model;  shape subspace;  search subspace;  principal component analysis
动态形状模型;  形状子空间;  搜索子空间;  主分量分析
PACS:
TP391
DOI:
10.3969/j.issn.1003-7985.2005.03.004
Abstract:
A novel idea, called the optimal shape subspace(OSS)is first proposed for optimizing active shape model(ASM)search.It is constructed from the principal shape subspace and the principal shape variance subspace.It allows the reconstructed shape to vary more than that reconstructed in the standard ASM shape space, hence it is more expressive in representing shapes in real life.Then a cost function is developed, based on a study on the search process.An optimal searching method using the feedback information provided by the evaluation cost is proposed to improve the performance of ASM alignment.Experimental results show that the proposed OSS can offer the maximum shape variation with reserving the principal information and a unique local optimal shape is acquired after optimal searching.The combination of OSS and optimal searching can improve the ASM performance greatly.
首先提出了最优形状子空间概念, 它由主要形状子空间和主要形状变化子空间联合构成, 最大程度上包含了搜索形状上的变化, 更贴近现实中要搜索的目标.然后, 在仔细研究了经典算法中的搜索过程后, 通过引入代价函数和反馈机制, 提出了一种最优搜索的概念, 使在搜索过程中搜索、评价、反馈不断地进行, 最后得到最佳的搜索结果.实验表明:提出的最优形状子空间在保证主要形状的基础上给出了最大限度的形状变化, 最优搜索过程可保证搜索到局部的惟一最优形状.它们的综合大大改善了动态形状模型的性能, 并提高了搜索的精确性.

References:

[1] 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.
[2] Rogers M, Graham J.Robust active shape model search [A].In:Proceedings of the European Conference on Computer Vision [C].Copenhagen, Denmark, 2002.517-530.
[3] Huang Xiangsheng, Li S Z, Wang Yangsheng.Evaluation of face alignment solutions using statistical learning [A].In:Proceedings of Sixth IEEE International Conference on Automatic Face and Gesture Recognition [C].Seoul, South Korea, 2004.213-218.
[4] Zhao Ming, Chen Chun, Li S Z, et al.Subspace analysis and optimization for AAM based face alignment [A].In: Proceedings of Sixth IEEE International Conference on Automatic Face and Gesture Recognition [C].Seoul, South Korea, 2004.290-295.
[5] Martinez A, Benavente R.The AR face database [R].Barcelona, Spain: Computer Vision Center(CVC), 1998.
[6] Phillips P J, Moon H, Rizvi S A, et al.The FERET evaluation methodology for face-recognition algorithms [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10):1090-1104.
[7] Li S Z, Zhang Zhenqiu.FloatBoost learning and statistical face detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9):1112-1123.

Memo

Memo:
Biographies: He Lianghua(1977—), male, graduate;Zou Cairong(corresponding author), male, doctor, professor, cairong@seu.edu.cn.
Last Update: 2005-09-20