Title: Local binary pattern based features for sign language recognition
Authors: Hrúz, Marek
Trojanová, Jana
Železný, Miloš
Citation: HRÚZ, Marek; TROJANOVÁ, Jana; ŽELEZNÝ, Miloš. Local binary pattern based features for sign language recognition. In: Pattern recognition and image analysis, 22, 4, p. 519-526. ISSN 1054-6618.
Issue Date: 2011
Publisher: Maik nauka-interperiodica publishing
Document type: článek
URI: http://www.kky.zcu.cz/cs/publications/HruzMarek_2011_LocalBinaryPattern
ISSN: 1054-6618
Keywords: local binary patterns;znaková řeč
Keywords in different language: local binary patterns;sign language
Abstract in different language: In this paper we focus on appearance features describing the manual component of Sign Language particularly the Local Binary Patterns. We compare the performance of these features with geometric moments describing the trajectory and shape of hands. Since the non-manual component is also very important for sign recognition we localize facial landmarks via Active Shape Model combined with Landmark detector that increases the robustness of model fitting. We test the recognition performance of individual features and their combinations on a database consisting of 11 signers and 23 signs with several repetitions. Local Binary Patterns outperform the geometric moments. When the features are combined we achieve a recognition rate up to 99.75% for signer dependent tests and 57.54% for signer independent tests.
Rights: © Marek Hrúz - Jana Trojanová - Miloš Železný
Appears in Collections:Články / Articles (NTIS)
Články / Articles (KKY)

Files in This Item:
File Description SizeFormat 
HruzMarek_2011_LocalBinaryPattern.pdfPlný text436,54 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/17183

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.