Improving Human Gait Recognition Using Feature Selection

摘要: Human gait, a biometric aimed to recognize individuals by the way they walk has recently come play an increasingly important role in visual surveillance applications. Most of existing approaches this area, however, have mostly been evaluated without explicitly considering most relevant gait features, which might compromised performance. In paper, we investigated effect discarding irrelevant or redundant employing Genetic Algorithms (GAs) select optimal subset on improving performance recognition system. Experimental results CASIA dataset demonstrate that proposed system achieves considerable