"Collection and Preprocessing of Czech Sign Language Corpus for Sign Language Recognition"@en . "This paper discusses the design, recording and preprocessing of a Czech sign language corpus. The corpus is intended for training and testing of sign language recognition (SLR) systems. The UWB-07-SLR-P corpus contains video data of 4 signers recorded from 3 different perspectives. Two of the perspectives contain whole body and provide 3D motion data, the third one is focused on signer?s face and provide data for face expression and lip feature extraction. Each signer performed 378 signs with 5 repetitions. The corpus consists of several types of signs: numbers (35 signs), one and two-handed finger alphabet (64), town names (35) and other signs (244). Each sign is stored in a separate AVI file. In total the corpus consists of 21853 video files in total length of 11.1 hours. Additionally each sign is preprocessed and basic features such as 3D hand and head trajectories are available." . "[4AB0F70215D9]" . "4"^^ . "Paris" . . "Tento \u010Dl\u00E1nek popisuje tvorbu, nahr\u00E1v\u00E1n\u00ED a p\u0159edzpracov\u00E1n\u00ED korpusu \u010Desk\u00E9ho znakov\u00E9ho jazyka. Korpus slou\u017E\u00ED pro tr\u00E9nov\u00E1n\u00ED a testov\u00E1n\u00ED automatick\u00FDch syst\u00E9m\u016F pro rozpozn\u00E1v\u00E1n\u00ED znakov\u00E9ho jazyka. Tento korpus UWB-07-SLP-P obsahuje videonahr\u00E1vky 4 znakuj\u00EDc\u00EDch osob, kter\u00E9 jsou nasn\u00EDm\u00E1ny za 3 pohled\u016F. Dva z nich zachyt\u00E1vaj\u00ED celou osobu, t\u0159et\u00ED je zam\u011B\u0159ena na obli\u010Dej. Ka\u017Ed\u00FD znakuj\u00EDc\u00ED provedl 378 znak\u016F, ka\u017Ed\u00FD p\u011Btkr\u00E1t opakov\u00E1n. Korpus obsahuje celkem 21853 videosoubor\u016F v d\u00E9lce 11,1 hodin. Ka\u017Ed\u00FD znak je p\u0159edzpracov\u00E1n a jsou dostupn\u00E9 z\u00E1kladn\u00ED p\u0159\u00EDznaky, jako nap\u0159. trajektorie rukou v 3D prostoru."@cs . "Collection and Preprocessing of Czech Sign Language Corpus for Sign Language Recognition" . "360352" . . "sign language recognition; czech sign language; image processing"@en . "2-9517408-4-0" . "Collection and Preprocessing of Czech Sign Language Corpus for Sign Language Recognition"@en . "Tvorba a p\u0159edzpracov\u00E1n\u00ED korpusu \u010Desk\u00E9ho znakov\u00E9ho jazyka pro automatick\u00E9 rozpozn\u00E1v\u00E1n\u00ED znakov\u00E9ho jazyka"@cs . "RIV/49777513:23520/08:00500083" . "Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)" . . . . . . . "ELRA" . "Campr, Pavel" . "Collection and Preprocessing of Czech Sign Language Corpus for Sign Language Recognition" . "Tvorba a p\u0159edzpracov\u00E1n\u00ED korpusu \u010Desk\u00E9ho znakov\u00E9ho jazyka pro automatick\u00E9 rozpozn\u00E1v\u00E1n\u00ED znakov\u00E9ho jazyka"@cs . "This paper discusses the design, recording and preprocessing of a Czech sign language corpus. The corpus is intended for training and testing of sign language recognition (SLR) systems. The UWB-07-SLR-P corpus contains video data of 4 signers recorded from 3 different perspectives. Two of the perspectives contain whole body and provide 3D motion data, the third one is focused on signer?s face and provide data for face expression and lip feature extraction. Each signer performed 378 signs with 5 repetitions. The corpus consists of several types of signs: numbers (35 signs), one and two-handed finger alphabet (64), town names (35) and other signs (244). Each sign is stored in a separate AVI file. In total the corpus consists of 21853 video files in total length of 11.1 hours. Additionally each sign is preprocessed and basic features such as 3D hand and head trajectories are available."@en . "Hr\u00FAz, Marek" . . . "23520" . "RIV/49777513:23520/08:00500083!RIV09-AV0-23520___" . "Trojanov\u00E1, Jana" . . . "3"^^ . . . . "3"^^ . "P(1ET101470416)" . . .