A novel hand gesture recognition method using Principal Directional Features

Author

Jasim, Mahmood ; Tao Zhang ; Hasanuzzaman, Md

Author_Institution

Dept. of Comput. Sci. & Eng., Univ. of Dhaka, Dhaka, Bangladesh

fYear

2013

fDate

12-14 Dec. 2013

Firstpage

1264

Lastpage

1269

Abstract

This paper presents a novel hand gesture recognition method based on Principal Directional Features (PDF). The image sequence is captured using a fixed mounted monocular camera to recognize dynamic gestures. Haar-like feature based cascaded classifier is used for hand area segmentation. Text based Principal Directional Features are extracted from the segmented images. Longest Common Subsequence algorithm is used to recognize the gestures from text based PDF. The Directional Gesture dataset is prepared containing complex dynamic gestures to test this system and achieved 94% accuracy in recognizing dynamic hand gestures.

Keywords

Haar transforms; feature extraction; gesture recognition; image classification; image segmentation; image sequences; Haar-like feature based cascaded classifier; directional gesture dataset; dynamic gesture recognition; dynamic hand gesture recognition; fixed mounted monocular camera; hand area segmentation; hand gesture recognition method; image sequence; longest common subsequence algorithm; principal directional features; text based PDF; text based principal directional feature extraction; Accuracy; Equations; Feature extraction; Gesture recognition; Image segmentation; Image sequences; Mathematical model;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Biomimetics (ROBIO), 2013 IEEE International Conference on

Conference_Location

Shenzhen

Type

conf

DOI

10.1109/ROBIO.2013.6739638

Filename

6739638