A note of fingerspelling recognition by hand shape using higher-order local auto-correlation features

The fingerspelling recognition by hand shape is an important step for developing a human-computer interaction system. A method of fingerspelling recognition by hand shape using higher-order local auto-correlation(HLAC) features is proposed. From the experimental results, the proposed method is promising. And to reduce image resolution and to thresholding an image are shown to be effective. In this paper, in order to further improve the fingerspelling recognition performance, we have proposed the use of division of an image in extracting HLAC features. The results show that the division of an image is effective for fingerspelling recognition by hand shape.