Recognizing Gait Using Haar Wavelet and Support Vector Machine
This paper presented a new gait identification method based on Haar wavelet and Support Vector Machine. It solves the problem how to select key points and employ features to classify gaits. Firstly, images from video sequences are converted into binary silhouette. Haar wavelet transform is employed to obtain key points for distinct features, and the key points are analyzed. A subimage is utilized to represent gait features in each image, and employ Principal Component Analysis to reduce its dimensionalities. Finally, Support Vector Machine is employ to train and test, and it is helpful in analyzing features. Consequently, we can not only simplify the process, but also improve the recognition accuracy.
Keywordsfeature extraction gait recognition Haar wavelet Support Vector Machine
Unable to display preview. Download preview PDF.
- 3.Kale, A., Cuntoor, N., Yegnanarayana, B., Rajagopalan, A.N., Chellappa, R.: Gait analysis for human identification. In: Proc. 4th Int. Conf. Audio- and Video-Based Person Authentication, Guilford, U.K., pp. 706–714 (2003)Google Scholar
- 4.Boulgouris, N.V., Plataniotis, K.N., Hatzinakos, D.: An angular transform of gait sequences for gait assisted recognition. In: Proc. IEEE Int. Conf. Image Processing, Singapore, pp. 857–860 (2004)Google Scholar
- 5.Zhang, H., Liu, Z., Zhao, H.: Automated Classification of Two Persons’ Interactive Activities. Journal of Software 5(8), 810–817 (2010)Google Scholar
- 6.Zhang, H., Liu, Z., Zhao, H., Cheng, G.: Recognizing Human Activities by Key Frame in Video Sequences. Journal of Software 5(8), 818–825 (2010)Google Scholar
- 11.Chen, S., Tian, Y., Huang, W., et al.: Automatic human gait recognition using temporal template. Journal of Xidian University 34(4), 605–610 (2007)Google Scholar
- 12.Ye, B., Wen, Y.: Gait recognition based on DWT and SVM. Journal of Image and Graphics 12(6), 1055–1063 (2007)Google Scholar