Abstract: A method using reflective symmetry of key frames is proposed in the paper as gait feature to recognize test sequence. Reflective symmetry implicitly represents the habit with which the leg and body of a person swings. Experiments on USF dataset show that the recognition rate by using symmetry feature with frequency feature and proportion of body is higher than only exploiting the frequency feature and the proportion. Reflective symmetry is not a unique but a useful feature and it can be easily combined with other features to improve the recognition rate. The proposed algorithm is simple to implement and insensitive to the changes of walking speed, background, and the clothing of the person.