Home // ACHI 2016, The Ninth International Conference on Advances in Computer-Human Interactions // View article

Text Input System Using Hand Shape Recognition

Authors:
Yang Keun Ahn
Kwang-Mo Jung

Keywords: Gesture Recognition; Text Input System; Hand Shape; Shape Recognition

Abstract:
This paper presents a method to recognize Korean language input using hand information extracted from 3D information taken from a single camera in a smart device environment. The presented method uses the shape information of an image of the hand as input for Korean mobile phone keyboards. Depth information is used to extract the region of the hand in real time. Through preprocessing, noise is removed from the extracted region, and the hand image is normalized with respect to its size and movement. The normalized image of the hand is projected using the rotation invariant Zernike basis function to ascertain its moment. These moment values of the hand’s shape are compared to values saved in a database, and the character that has the closest moment value is input. The proposed method, which is designed to overcome the obstacle that people have unique hand shapes, makes use of a system that can easily become familiarized with an individual’s hand shape information.

Pages: 74 to 78

Copyright: Copyright (c) IARIA, 2016

Publication date: April 24, 2016

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-468-8

Location: Venice, Italy

Dates: from April 24, 2016 to April 28, 2016