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

fYear

2011

fDate

13-18 Sept. 2011

Firstpage

1138

Lastpage

1139

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;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE Annual Conference (SICE), 2011 Proceedings of

Conference_Location

Tokyo

ISSN

pending

Print_ISBN

978-1-4577-0714-8

Type

conf

Filename

6060503