Comparison study of different feature classifiers for hand posture classification

Author

Jeonghyun Baek ; Jisu Kim ; Euntai Kim

Author_Institution

Sch. of Electr. & Electron. Eng., Yonsei Univ., Seoul, South Korea

fYear

2013

fDate

20-23 Oct. 2013

Firstpage

683

Lastpage

687

Abstract

Hand posture classification has attracted much attention in Human-Computer Interaction (HCI). In hand posture classification, vision based approach is popularly used. However, it has difficulty of dealing with illumination change and pose variation. In this paper, we compare the performance of combination with features, which are HOG, LBP, and classifiers, which are SVM and Neural Network for hand posture classification. Experiments are performed with Cambridge hand gesture dataset.

Keywords

feature extraction; gesture recognition; gradient methods; human computer interaction; image classification; lighting; neural nets; pose estimation; support vector machines; Cambridge hand gesture dataset; HCI; HOG; LBP; SVM; feature classifiers; hand posture classification; human-computer interaction; illumination change; neural network; pose variation; vision based approach; Biology; Kernel; Polynomials; Rocks; Solid modeling; Three-dimensional displays; Training; HOG; Hand posture classification; LBP; Neural network; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Automation and Systems (ICCAS), 2013 13th International Conference on

Conference_Location

Gwangju

ISSN

2093-7121

Print_ISBN

978-89-93215-05-2

Type

conf

DOI

10.1109/ICCAS.2013.6703956

Filename

6703956