Low-Resolution Gait Recognition

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.

• Type: Journal
• Year: 2010
• Where: TSMC
• Authors: Junping Zhang, Jian Pu, Changyou Chen, Rudolf Fleischer
• Keywords: Artificial Intelligence, Low Resolution, Low Resolution Counterpart, Low Resolution Sequence, TSMC 2010