Název:	Local binary pattern based features for sign language recognition
Autoři:	Hrúz, Marek Trojanová, Jana Železný, Miloš
Citace zdrojového dokumentu:	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.
Datum vydání:	2011
Nakladatel:	Maik nauka-interperiodica publishing
Typ dokumentu:	článek article
URI:	http://www.kky.zcu.cz/cs/publications/HruzMarek_2011_LocalBinaryPattern http://hdl.handle.net/11025/17183
ISSN:	1054-6618
Klíčová slova:	local binary patterns;znaková řeč
Klíčová slova v dalším jazyce:	local binary patterns;sign language
Abstrakt v dalším jazyce:	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.
Práva:	© Marek Hrúz - Jana Trojanová - Miloš Železný
Vyskytuje se v kolekcích:	Články / Articles (NTIS) Články / Articles (KKY)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.