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

Alphabet Recognition in Air Writing Using Depth Information

Authors:
Robiul Islam
Hasan Mahmud
Md. Kamrul Hasan
Husne Ara Rubaiyeat

Keywords: Air Writing; Gesture Recognition; Depth Infor-mation; Time Series; Dynamic Time Warping

Abstract:
We present a data mining approach to recognize air written English Capital Alphabets (ECAs) using depth information. The hand motion while writing the alphabet in the air was captured as depth images by a depth camera. The depth images were then processed as the hand movement time series data, which was matched with standard templates of air writing by Dynamic Time Warping (DTW) algorithm. We collected a dataset of five variations and from them standardized 20 templates for each ECA. The accuracy for ECA is 93-99% with an average of 96.3%.

Pages: 299 to 301

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