Title :
A study of fingerspelling recognition by hand shape using higher-order local auto-correlation features
Author :
Kanemura, Takuya ; Mitani, Yoshihiro ; Fujita, Yusuke ; Hamamoto, Yoshihiko
Author_Institution :
Ube Nat. Coll. of Technol., Ube, Japan
Abstract :
The fingerspelling recognition by hand shape is an important step for developing a human-computer interaction system. In this paper, we have proposed a method of fingerspelling recognition by hand shape using higher-order local auto-correlation features. Furthermore, in order to improve the fingerspelling recognition performance, we have also proposed to apply image processing techniques of reducing image resolution and thresholding an image. The results show that the proposed method is effective for fingerspelling recognition by hand shape.
Keywords :
correlation methods; feature extraction; human computer interaction; image recognition; image resolution; image segmentation; shape recognition; fingerspelling recognition; hand shape; higher-order local autocorrelation feature; human-computer interaction system; image processing technique; image resolution reduction; image threshold; Error analysis; Feature extraction; Image recognition; Image resolution; Shape; Training; Binarization; Fingerspelling Recognition by Hand Shape; HLAC features; Image Processing Techniques; Reduction of Image Resolution;
Conference_Titel :
SICE Annual Conference (SICE), 2011 Proceedings of
Conference_Location :
Tokyo
Print_ISBN :
978-1-4577-0714-8
