Human Gait Recognition Based on Kernel PCA Using Projections

被引:4
作者
Murat Ekinci
Murat Aykut
机构
[1] Computer Vision Lab Department of Computer Engineering
[2] 61080 Trabzon
[3] Karadeniz Technical University
[4] Turkey
关键词
biometrics; gait recognition; gait representation; kernel PCA; pattern recognition;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
This paper presents a novel approach for human identification at a distance using gait recognition.Recog- nition of a person from their gait is a biometric of increasing interest.The proposed work introduces a nonlinear machine learning method,kernel Principal Component Analysis (PCA),to extract gait features from silhouettes for individual recognition.Binarized silhouette of a motion object is first represented by four 1-D signals which are the basic image features called the distance vectors.Fourier transform is performed to achieve translation invariant for the gait patterns accumulated from silhouette sequences which are extracted from different circumstances.Kernel PCA is then used to extract higher order relations among the gait patterns for future recognition.A fusion strategy is fiinally executed to produce a final decision.The experiments are carried out on the CMU and the USF gait databases and presented based on the different training gait cycles.
引用
收藏
页码:867 / 876
页数:10
相关论文
共 21 条
  • [1] Automatic recognition by gait. Nixon M S,Carter J N. Pro- ceeding of the IEEE . 2006
  • [2] What image information is important in silhouette-based gait recogni- tion. Veres G V,Gordon L,Carter J N,Nixon M S. Proc.IEEE Confence on Computer Vision and Pattern Recognition . 2004
  • [3] The HumanID gait challenge problem:Data sets,performance,and analysis. Sarkar S et al. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2005
  • [4] The CMU motion of body (MoBo) database. R. Gross and J. Shi. . 2001
  • [5] Motion-based recog- nition of people in eigengait space. BenAbdelkader C,Cutler R,Davis L. Proc.International Conference on Automatic Face and Gesture Recognition . 2002
  • [6] Gait verification using probabilis- tic methods. Basin A I,Nixon M S. Proc.IEEE Workshop on Applications of Computer Vision . 2005
  • [7] Identification of humans using gait. Kale Aet al. IEEE Transactions on Image Processing . 2004
  • [8] Silhouette-based human identi- fication from body shape and gait. Collins R,Gross R,Shi J. Proc.International Conference on Automatic Face and Gesture Recognition . 2002
  • [9] Silhouette analysis-based gait recognition for human identification. Liang Wang,Tieniu Tan. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2003
  • [10] Gait-based recognition of humans using continuous HMMMs. Kale A,Rajagopalan A,Cuntoor N,Krugger V. Proc. IEEE International Conference on Automatic Face and Gesture Recognition . 2002