Title: | Evaluation of feature space transforms for czech sign-language recognition |
Authors: | Trmal, Jan Hrúz, Marek |
Citation: | TRMAL, Jan; HRÚZ, Marek. Evaluation of feature space transforms for czech sign-language recognition. In: MetaCentrum Yearbook 2010. Brno: Masaryk University, 2010, p. 145-150. ISBN 978-80-904173-7-3. |
Issue Date: | 2010 |
Publisher: | Masaryk University |
Document type: | článek article |
URI: | http://www.kky.zcu.cz/cs/publications/TrmalJan_2010_EvaluationofFeature http://hdl.handle.net/11025/16967 |
ISBN: | 978-80-904173-7-3 |
Keywords: | rozpoznávání znakové řeči;parametrizace |
Keywords in different language: | sign language recognition;parametrization |
Abstract in different language: | In the paper we give a brief introduction into sign language recognition and present a particular research task, where the access to MetaCentrum computing facilities was highly beneficial. Although the problem of signed speech recognition is currently being researched into by many research institutions all around the world, it lacks of a generally accepted baseline parametrization method. Our team introduced a parametrization method based on skin-color detection and object tracking. Because of the relatively high amount of information that is produced during the parametrization process, a method that reduces the unnecessary information while keeping the necessary information is required. Such methods are called feature space dimension reduction methods. We used the MetaCentrum facilities to evaluate several methods used widely in the field of acoustic speech recognition and their influence on recognition score of a Czech Sign-Language recognizer. |
Rights: | © Jan Trmal - Marek Hrúz |
Appears in Collections: | Články / Articles (KKY) Články / Articles (NTIS) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
TrmalJan_2010_EvaluationofFeature.pdf | Plný text | 450,15 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/16967
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.