Gesture Recognition Algorithm Based on Contour Sequence Recursive Model

To improve the accuracy and robustness, a novel algorithm CSRP is proposed based on compression distance of recurrence patterns extracted from the perspective of edge sequence. Firstly, the regional images of the hand with fingertips are obtained by threshold segmentation, and then, the edge sequences of palms are built following the change of the spatial position from the start point; In order to overcome the problem of unequal length of the edge sequences, recurrence plots in spatial domain are established; Finally, CK-1 distance is calculated by using the MPEG-1 video compression algorithm for gesture recognition. The experimental results show that the proposed algorithm achieves high robustness in the case of rotation, translation and scaling, with 97% recognition accuracy.