基于加权主动形状建模的人脸特征定位方法

冀贞海; 孙宁; 邹采荣; 赵力

doi:10.3724/SP.J.1146.2005.01674

基于加权主动形状建模的人脸特征定位方法

doi: 10.3724/SP.J.1146.2005.01674

冀贞海^{①②;孙宁},
孙宁,
邹采荣,
赵力

基金项目:

国家自然科学基金项目(60503023)和教育部博士点基金(200502860 01)资助项目

计量
- 文章访问数: 3101
- HTML全文浏览量: 85
- PDF下载量: 1312
- 被引次数: 0
出版历程
- 收稿日期: 2005-12-26
- 修回日期: 2006-06-26
- 刊出日期: 2007-04-19

Face Alignment Based on Weighted Active Shape Models

摘要

摘要: 主动形状建模是面部特征定位和人脸识别等模式识别领域中常用的一种方法。然而，由于受到初始情况、光照等诸多因素的影响，主动形状建模经常会陷入最优化过程中的局部最小问题，从而导致其性能下降。该文在传统主动形状模型基础上，提出了一种加权主动形状建模的方法，该方法可以有效地解决上述局部最小问题，并且更好地捕捉局部点的特征信息，从而更精确地进行面部特征定位。最后通过实验验证了上面的结论。
- 人脸识别;面部特征定位;主动形状模型;局部形状建模
Abstract: Active Shape Models (ASM) is one of powerful tools for face alignment and face recognition. However, the performance of ASM is often influenced by some factors such as the initial location, illumination and so on, which will frequently lead to the local minima in optimization. This paper proposes a weighted Active Shape Models, in which the more robust local appearance model is constructed with the local information of each landmark fully. Through the improved method the local minima problem can be solved efficiently, extracted the detailed local information of face feature points and localized the points accurately. Experiments verify the above conclusions.

HTML全文

参考文献(1)

[1] Beinglass A and Wolfson H J. Articulated object recognition, or: How to generalize the generalized Hough transform[C]. In proceedings IEEE computer society conference on computer vision and pattern Recognition, Hawaii，1991: 461-466. [2] Kass M, Witkin A, and Terzopoulos D. Snakes: Active contour models[C]. 1st International Conference on Computer Vision, London, 1987: 259-268. [3] Wiskott L, Fellous J M, and Kruger N, et al.. Face recognition by Elastic Graph Matching[C]. Interlligent Biometric Techniques in Fingerprint and Face Recognition, Eds. Jain L.C. et al.,Washington DC.,pub1. CRC Press, 1999: 355-396. [4] Nastar C and Ayache N. Fast segmentation, tracking and analysis of deformable objects[C]. International Conference on Computer Vision, Berlin, 1993: 275-279. [5] Cootes T F and Taylor C J, et al.. Active shape models - their training and application[J].Computer Vision and Image Understanding.1995, 61(1):38-59 [6] Cootes T F, Edwards G J, and Taylor C J. Active appearance models[C]. European Conference On Computer Vision. Berlin, 1998, vol.2: 484-498. [7] Zhao M, Li S Z, Chen C, and Bu J J. Shape evaluation for weighted active shape models[C]. Asian Conference on Computer Vision, Korea, 2004 vol.2: 1074-1079. [8] Jiao F, and Li S Z, et al.. Face alignment using statistical models and wavelet features[C]. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Wisconsin, 2003, Vol.1: 321-327. [9] Cootes T F, and Hill A, et al.. The use of active shape models for locating structures in medical images[J]. Image Vision Comput., 1994, 12(6): 355-366. [10] Stegmann M B, Ersbll B K, and Larsen R. FAMEA flexible appearance modeling environment[J].IEEE Trans. on Medical Imaging.2003, 22(10):1319-1331 [11] Athinodoros S G and Peter N B. From few to many: Illumination cone models for face recognition under variable lighting and pose[J]. IEEE Trans. on PAMI, 2001, 23(6): 643 -660.

施引文献

资源附件(0)

访问统计