CFP last date
22 July 2024
Reseach Article

Topic Model for Person Identification using Gait Sequence Analysis

by Deepak N.A., Sinha U.N.
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 133 - Number 7
Year of Publication: 2016
Authors: Deepak N.A., Sinha U.N.

Deepak N.A., Sinha U.N. . Topic Model for Person Identification using Gait Sequence Analysis. International Journal of Computer Applications. 133, 7 ( January 2016), 1-6. DOI=10.5120/ijca2016907892

@article{ 10.5120/ijca2016907892,
author = { Deepak N.A., Sinha U.N. },
title = { Topic Model for Person Identification using Gait Sequence Analysis },
journal = { International Journal of Computer Applications },
issue_date = { January 2016 },
volume = { 133 },
number = { 7 },
month = { January },
year = { 2016 },
issn = { 0975-8887 },
pages = { 1-6 },
numpages = {9},
url = { },
doi = { 10.5120/ijca2016907892 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
%0 Journal Article
%1 2024-02-06T23:30:40.555967+05:30
%A Deepak N.A.
%A Sinha U.N.
%T Topic Model for Person Identification using Gait Sequence Analysis
%J International Journal of Computer Applications
%@ 0975-8887
%V 133
%N 7
%P 1-6
%D 2016
%I Foundation of Computer Science (FCS), NY, USA

Gait sequence analysis from the input binary silhouettes, has various applications, such as person identification, human action recognition, event recognition and classification. The gait feature extraction is a key step in gait analysis. The ’Topic Model’, used for text classification, is one of the potential semantic approaches to study gait sequence analysis. The proposed algorithm uses Latent Dirichlet Allocation (LDA), a ’Topic Model’, to analyse the gait sequence for person identification. This has been achieved by proposing a novel transformation method that transforms the gait sequence into word representation suitable for topic models like LDA. The latent dirichlet allocation algorithm, then calculates the word-topic and topic-image distributions, using the words generated by transforming the gait sequences using a transformation method. Finally, the image-topic-word distributions are used to identify person. The performance of the proposed latent dirichlet allocation algorithm, has been illustrated using CASIA dataset A, dataset B and TUM-IITKGP gait dataset, resulting in an average classification rate of 82.2% using dataset B, and 85%, 85%, and 85% for lateral, oblique and frontal view respectively with respect to dataset A and 90% using TUM-IITKGP gait dataset.

  1. Dong, M., Cong, Z., Yanru, B., Baikun, W., and Yong, H. 2009. Gait Recognition Based on Multiple Views Fusion of Wavelet Descriptor and Human Skeleton Model. IEEE International Conference on Virtual Environments, Human-Computer Interfaces and Measurements Systems. 246-249.
  2. Jinyan, C., and Jiansheng, L. 2014. Average Gait Differential Image Based Human Recognition. Scientific World Journal. Vol. 2014. 1-8.
  3. Jinyan, C. 2014. Gait Correlation Analysis Based Human Identification. Scientific World Journal. Vol. 16. 275-283.
  4. Muhammad, R. A., and Koichi, S. 2012. Efficient Model Training for HMM-based Person Identification by Gait. IEEE Signal and Information Processing. 1-4.
  5. Chiraz, B., Ross, C., and Larry D. 2002. View-Invariant Estimation of Height and Stride for Gait Recognition. Biometric Authentication ECCV: Int. Workshop. Vol. 4, 155-167.
  6. Yasushi, Sagawa, R., Mukaigawa, Y., and Echigo, T. 2006. Gait Recognition using a view Transformation Model in a Frequency Domain. IPSJ SIG Technical Reports. Vol. 6, 117-124.
  7. Hu, N., Hau-Lee, T., Wooi-Haw, T., and Timothy Tzen-Vun, Y. 2011. Human Identification Based on Extracted Gait Features. Int. Journal on New Computer Architectures and Their Applications. Vol. 1, 358-370.
  8. Emdad, H., and Girija, C. 2012. Person Identification in Surveillance Video Using Gait Biometric cues. Int. Conference on Fuzzy Systems and Knowledge Discovery. 1877-1881.
  9. Nikolaos, V. B., and Konstantinos, N. P. 2006. Gait Recognition using Linear Time Normalization. IEEE Pattern Recognition Letters. Vol. 39, 969-979.
  10. Yumi, I., and Koji, U. 2013. Gait-Based Person Identification Robust to Changes in Appearance. Sensors. Vol. 13, 7884- 7901.
  11. Jiwen, L., and Erhu, Z. 2007. Gait Recognition for Human Identification based on ICA and Fuzzy SVM Through Views Fusion. IEEE Pattern Recognition Letters. Vol. 28, 2401-2411.
  12. Liang, W., Tieniu, T., Huazhong, N., and Weiming. H. 2003. Silhouette Analysis-Based Gait Recognition for Human Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 25, 1505-1518.
  13. Ran, H., and Tieniu, T. 2014. Robust Recovery of Corrupted Low-Rank Matrix by Implicit Regularizers. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 36, 770- 783.
  14. Shiqi, Y., Daoliang, T., and Tieniu, T. 2006. A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition. Int. Conference on Pattern Recognition. Vol. 4, 441-444.
  15. Zheng, S., Zhang, J., Huang, K., He, R., Tan, T. 2011. Robust View Transformation Model for Gait Recognition. Int. Conference on Image Processing. 2073-2076.
  16. Martin, H., Shamik, S., and Gerhard, R. 2011. Gait Recognition in the Presence of Occlusion: A New Dataset and Baseline Algorithms. Int. Conferences on Computer Graphics, Visualization and Computer Vision.
  17. Murat, E. 2006. A New Attempt to Silhouette-Based Gait Recognition for Human Identification. Computer Science Journals. Vol. 4013, 443-454.
  18. Liang, W., Tieniu, T., and Weiming, H. 2003. Automatic Gait Recognition Based on Statistical Shape Analysis. IEEE Transactions on Image Processing. Vo. 12, 1120-1131.
  19. Zhang, Y.,Wu, X., and Guo, T. 2009. Robust Post-processing Strategy for Gait Silhouette. IEEE Int. Conference on Computer Science and Information Technology. 476-479.
  20. Changhong, C., Jimin, L., and Xiuchang, Z. 2011. Gait Recognition Based on Improved Dynamic Bayesian Networks. IEEE Pattern Recognition Letters. Vol. 44, 988-995.
  21. Javier, L. L., and Edel, G. R. 2009. Human Gait Recognition using Topological Information. Springer. Vol. 1, 244-251.
  22. Hayder, A., Jamal, D., Chekima, A., and Ervin. G. M. 2011. Gait Recognition using Gait Energy Image. Int. Journal of Signal Processing, Image Processing and Pattern Recognition. Vol. 4, 141-152.
  23. Daigo, M., Akira, S., and Yasushi, M. 2015. Gait-Based Person Recognition using Arbitrary View Transformation Model. IEEE Transactions on Image Processing. Vol. 2,140-154.
  24. Takuhio, K., Yasushi, M., Diago, M., and Yasushi, Y. 2014. Quality Dependent Score Level Fusion of Face, Gait and Height Biometrics. IPSJ Transactions on computer vision and Applications. Vol. 6, 53-57.
  25. Chunsheng, H., Yasushi. M., and Yasushi, Y. 2013. Pedestrian Detection by using Spatio Temporal Histogram of Oriented Gradients. IEICE Trans.INF & SYST. Vol. 96, 1376-1386.
  26. Mansur, A., Yasushi, M., and Yasushi, Y. 2013. Inverse Dynamics for Action Recognition. IEEE Transaction on Cybernetics. Vol. 43, 1226-1236.
Index Terms

Computer Science
Information Sciences


Gait Analysis Gait Sequence Latent Dirichlet Allocation Person Identification Primary Gait Sequence.