Low Resolution Gait Recognition with High Frequency Super Resolution
Being non-invasive and effective at a distance, recognition suffers from low resolution sequence case. In this paper, we attempt to address the issue through the proposed high frequency super resolution method. First, a group of high resolution training gait images are degenerated for capturing high-frequency information loss. Then the combination of neighbor embedding with interpolation methods is employed for learning and recovering a high resolution test image from low resolution counterpart. Finally, classification is performed based on nearest neighbor classifier. The experiment indicates that the proposed method can effectively improve the accuracy of gait recognition under low resolution case.
KeywordsGait Recognition Super Resolution Gait Energy Image
Unable to display preview. Download preview PDF.
- 2.Kobayashi, T., Otsu, N.: Action and simultaneous multiple-person identification using cubic higher-order local auto-correlation. In: Proceedings of the 17th International Conference on Pattern Recognition, Cambridge (2004)Google Scholar
- 3.Horita, Y., Ito, S., Kaneda, K., Nanri, T., Shimohata, Y., Taura, K., Otake, M., Sato, T., Otsu, N.: High precision gait recognition using a large-scale pc cluster. In: Proceedings of the 3rd IFIP International Conference on Network and Parallel Computing (2006)Google Scholar
- 4.Liu, Z., Sarkar, S.: Simplest representation yet for gait recognition: Averaged silhouette. In: Proc. IEEE International Conference on Pattern Recognition, vol. 4, pp. 211–214 (2004)Google Scholar
- 7.Chang, H., Yeung, D.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 275–282 (2004)Google Scholar