期刊文献+

基于分级边缘方位场匹配的人脸特征定位 被引量:2

Hierarchical Edge Orientation Field Matching Based Facial Feature Localization
下载PDF
导出
摘要 针对大范围姿态角度问题,提出了一种分级边缘方位场匹配(HEOFM)的人脸特征定位算法。提出了结构Hausdoff距离作为边缘方位场匹配的测度;在此基础上,先根据人脸图像的整体边缘方位场匹配(GEOFM)进行了姿态预估计,得到特征的粗略定位;然后根据特征边缘方位场匹配(FEOFM)在局部区搜索,实现特征的精确定位。实验结果表明:针对小姿态角度人脸图像,与一般的特征检测算法相比,该算法所需训练样本个数较少而定位精度相当;针对中、大姿态角度人脸图像,该算法具有良好的特征定位性能。 In order to improve the facial feature localization under large-scale pose angle, a hierarchical edge orientation field rnatching(HEOFM) based algorithm was proposed. A new measurement coined structural Hausdoff distance was developed for edge orientation field matching. The global edge orientation field matching(GEOFM) was applied to estimate the pose angle and thus obtain the coarse position of the features, and then the further local feature edge orientation field matching (FEOFM) was carded out for precise localization. The experimental results show that, this algorithm achieves almost high localization accuracy with less training examples compared with common detection based localization algorithm under small pose angle,and performs fairly good under moderate or large pose angle.
作者 陈华杰 韦巍
出处 《光电子.激光》 EI CAS CSCD 北大核心 2007年第2期241-244,共4页 Journal of Optoelectronics·Laser
基金 浙江省青年人才培养资助项目(R105341)
关键词 人脸特征定位 大范围姿态角度 分级边缘方位场匹配(HEOFM) 结构Hausdoff距离 facial feature localization large-scale pose angle hierarchical edge orientation field matching(HEOFM) structural Hausdoff distance
  • 相关文献

参考文献8

  • 1于威威,滕晓龙,刘重庆.一种快速准确的人眼定位方法[J].光电子.激光,2005,16(4):479-483. 被引量:5
  • 2杜成,苏光大,林行刚,顾华.改进的线段Hausdorff距离人脸识别方法[J].光电子.激光,2005,16(1):89-93. 被引量:10
  • 3Coates T F,Taylor C,Cooper D,et al.Active shape modelstheir training and their applications[J].Computer Vision and Image Understanding,1995,1 (16):38-59.
  • 4Campadelli P,Lanzarotti R,Lipori G.Face localization in color images with complex background[A].IEEE International Workshop on Computer Architecture for Machine Perception(CAMP)[C].Palermo,2005.
  • 5Gourier N,Hall D,Crowley J L.Estimating face orientation from robust detection of salient facial features[A].Visual Observation of Deictic Gestures[C].Cambridge,2004.
  • 6Feris R S,Gemmelll J,Toyama K,et al.Hierarchical.wavelet networks for facial feature localization[A].Fifth IEEE International Conference on Automatic Face and Gesture Recognition[C].2002,118-123.
  • 7Chen L,Zhang L,Zhang H,et al.3-D shape constraint for facial feature localization using probabilistic-like output[A].Sixth IEEE International Conference on Automatic Face and Gesture Recognition[C].2004,302-307.
  • 8Bernhard Fr(o)ba,Andreas Ernst.Fast frontal-view face detection using a multi-path decision tree[A].AVBPA[C].2003,921-928.

二级参考文献14

  • 1丁嵘,戴琼海,徐文立,苏光大,尹浩.大样本库人脸识别的分级弹性匹配算法[J].光电子.激光,2004,15(10):1238-1241. 被引量:4
  • 2顾华,苏光大,杜成.人脸关键特征点的自动定位[J].光电子.激光,2004,15(8):975-979. 被引量:16
  • 3WANG Wei, SHAN Shi-guang, GAO Wen, et al. An improved active shape model for face alignment [A]. In:Fourth IEEE International Conference on Multimodal Interfaces[C]. 2002. 523-528.
  • 4Kass M,Witkin A,Terzopoulos D. Snakes:Active contour models[A]. In:First International Conference on Computer Vision [C]. London: IEEE computer Soc., 1987. 259-268.?A
  • 5Yuille A, Cohen D, Hallinan P. Feature extraction from faces using deformable templates[J]. International Journal of Computer Vision,1992,8(2) :99-112.
  • 6Cootes 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.
  • 7Cootes T F, Edwards G, Taylor C. Active appearance models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(6) :681-685.
  • 8Biederman I,Gu J. Surface versus edge-based determinants of visual recognition[J]. Cognitive Psychol, 1998,20:38-64.
  • 9Bruce V. The importance of ‘Mass’ in line drawings of faces[ J]. Applied Cognitive Psychology, 1992,6: 619-628.
  • 10Takacs B,Wechsler H. Face recognition using binary image metrics [A]. In: Third IEEE International Conference on Automatic Face and Gesture Recognition [C]. 1998.294-299.?A

共引文献13

同被引文献26

  • 1邓世伟,袁保宗.基于数学形态学的深度图像分割[J].电子学报,1995,23(4):6-9. 被引量:22
  • 2武妍,杨洋,王丽萍.基于灰度信息和瞳孔滤波器的人眼定位算法[J].计算机工程与应用,2005,41(33):45-47. 被引量:11
  • 3孔令富,赵飞,赵逢达.腐蚀/膨胀算法在足球机器人视觉系统中的应用[J].计算机工程与应用,2007,43(24):200-202. 被引量:8
  • 4STEPHEN J M, SHAOGANG G, YOGESH R. Model- ling facial colour and identify with Gaussian mixtures[ J ].Pattern Recognition, 1998, 31 ( 12 ) : 1883-1892.
  • 5ZHAO M, SUN D H, HE H P. Hair-color modeling and head detection[C]//Proceedings of the 7th World Con- gress on Intelligent Control and Automation. Chongqing: IEEE Press, 2008:7768-7772.
  • 6MUNOZ I B, MOLINA P J, GALILEA J L L. Embed- ded vision modules for tracking and counting people[ J ]. IEEE Transactions on Instrumentation and Measurement, 2009, 58(9) :3004-3011.
  • 7BIRCHF1ELD S. Elliptical head tracking using intensity gradients and color histograms [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recog- nition. Santa Barbara: IEEE Press, 1998:232-237.
  • 8JIN Y G. Towards robust head tracking by particles [ C ]//IEEE Conference on Image Processing. Guild- ford, UK: IEEE Press, 2005 : III-864-867.
  • 9DINESH K V P, TESSAMMA T. Performance study of an improved legendre moment descriptor as region-based shape descriptor [ J ]. Pattern Recognition and Image Analysis, 2008, 18( 1 ) :23-29.
  • 10何新英,王家忠,孙晨霞,常淑惠,周桂红.基于数学形态学和Canny算子的边缘提取方法[J].计算机应用,2008,28(2):477-478. 被引量:34

引证文献2

二级引证文献20

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部