Gait Recognition Algorithm Based on Feature Fusion of GEI Dynamic Region and Gabor Wavelets
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI)dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted throughthe object detection, binarization and morphological process. Secondly, features of GEI at different angles andGabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Thenaveraging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets onfeature layer and the feature space dimension is reduced by an improved Kernel Principal ComponentAnalysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM)based on multi classification to realize the classification and recognition of gait. The primary contributions ofthe paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor isproposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed toidentify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% ofcorrect classification rate, which testify that the method can identify better different human gait and get betterrecognized effect than other existing algorithms.
Abstract
The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI)dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted throughthe object detection, binarization and morphological process. Secondly, features of GEI at different angles andGabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Thenaveraging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets onfeature layer and the feature space dimension is reduced by an improved Kernel Principal ComponentAnalysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM)based on multi classification to realize the classification and recognition of gait. The primary contributions ofthe paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor isproposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed toidentify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% ofcorrect classification rate, which testify that the method can identify better different human gait and get betterrecognized effect than other existing algorithms.
참고문헌 (28)
- N. V. Boulgouris, "Gait recognition: a challenging signal processing technology for biometric identification", IEEE Signal Processing Magazine, 22(6), pp.78~90 (2005)[DOI]
- Computer Graphics Collaboration Techniques and Applications, "Computer Vision", pp.2007, I. Bouchrika
- C. Wang, "Human identification using temporal information preserving gait template", IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), pp.2164~2176 (2012)[DOI]
- J. Han, "Individual recognition using gait energy image", IEEE Transactions on Pattern Analysis & Machine Intelligence, 28(2), pp.316~322 (2006)[DOI]
- Y. Makihara, "Individualitypreserving silhouette extraction for gait recognition", IPSJ Transactions on Computer Vision and Applications, 7, pp.74~78 (2015)[DOI]
- E. Zhang, "Active energy image plus 2DLPP for gait recognition", Signal Processing, 90(7), pp.2295~2302 (2010)[DOI]
- Y. Li, "Gait recognition based on dual view and multiple feature information fusion", CAAI Transactions on Intelligent Systems, 8(1), pp.74~79 (2013)
- J. Wu, "Advances in Natural Computation", pp.560~569, Springer
- Q. Yang, "Gait recognition based on active energy image and parameter-adaptive kernel PCA", Proceedings of 2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC), pp.156~159 (2011)
- S. Fazli, "Gait recognition using SVM and LDA", Proceedings of International Conference on Advances in Computing, Control, and Telecommunication Technologies, pp.106~109 (2011)
- L. Qiao, "Sparsity preserving projections with applications to face recognition", Pattern Recognition, 43(1), pp.331~341 (2010)[DOI]
- K. Wang, "Kernel sparsity preserving projections and its application to gait recognition", Journal of Image and Graphics, 18(3), pp.257~263 (2013)
- R. Atta, "Human identification based on temporal lifting using 5", 3 wavelet filters and radon transform, 2017, pp.69, 213~224
- J. Yang, "Two-dimensional PCA: a new approach to appearance-based face representation and recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(1), pp.131~137 (2004)[DOI]
- D. Y. Huang, "Gait recognition based on Gabor wavelets and modified gait energy image for human identification", Journal of Electronic Imaging, 22(4) (2013)
- B. A. Abdullah, "Statistical Gabor-based gait recognition using region-level analysis", Proceedings of 2015 IEEE European Modelling Symposium (EMS), pp.137~141 (2015)
- H. Shao, "Gait recognition method based on integrated Gabor feature", Journal of Electronic Measurement and Instrumentation, 31(4), pp.573~579 (2017)
- X. Wang, "Gait recognition based on Gabor wavelets and (2D)2PCA", Multimedia Tools and Applications, 77(10), pp.12545~12561 (2018)[DOI]
- S. Sarkar, "The humanID gait challenge problem: data sets, performance, and analysis", IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(2), pp.162~177 (2005)[DOI]
- D. H. Liu, "Optimal sampling of Gabor features for face recognition", Pattern Recognition Letters, 25(2), pp.267~276 (2004)[DOI]
- T. S. Lee, "Image representation using 2D Gabor wavelets", IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(10), pp.959~971 (1996)[DOI]
- "CASIA Gait Database" (2005)[URL]
- D. M. Tax, "Combining multiple classifiers by averaging or by multiplying?", Pattern Recognition, 33(9), pp.1475~1485 (2000)[DOI]
- K. Yan, "Online fault detection methods for chillers combining extended Kalman filter and recursive one-class SVM", Neurocomputing, 228, pp.205~212 (2017)[DOI]
- D. K. Vishwakarma, "Human activity recognition based on spatial distribution of gradients at sublevels of average energy silhouette images", IEEE Transactions on Cognitive and Developmental Systems, 9(4), pp.316~327 (2017)[DOI]
- P. Liu, "Gait recognition method based on Poisson distribution on Gabor wavelet", Computer Engineering and Applications, 51(Suppl), pp.1~5 (2015)
- Y. Ji, "A feature fusion based gait recognition algorithm", Journal of Electrical & Electronic Education, 3(5), pp.67~70 (2009)
- H. Chen H, "Front-view gait recognition based on the fusion of static and dynamic features", Opto-Electronic Engineering, 41, pp.83~88 (2013)