Gait recognition systems have recently attracted much interest from biometric researchers. This work proposes a new feature extraction method for gait representation and recognition. The new method is extended from the technique of Local Binary Pattern (LBP) by changing the sorting method of LBP according to the blend direction to create a new approach, Conditional-Sorting Local Binary Pattern (CS-LBP). After synchronizing and calibrating the gait sequence images, a cycle of images from the gait sequence can be captured to form a Gait Energy Image (GEI). We then apply the CS-LBP on GEI to derive different blend direction images and calculate the recognition ability for each blend direction image for feature selections. To solve the classification problem, the Euclidean distance and Nearest Neighbor (NN) approaches are used. With the experiments carried out on the CASIA-B gait database, our proposed gait representation has a very good recognition rate.
Proceedings of the International Conference on Image Processing, Computer Vision, & Pattern Recognition (IPCV 2013), 6p.