@inproceedings{campr:10043:sign-lang:lrec, author = {Campr, Pavel and Hr{\'u}z, Marek and Langer, Ji{\v r}{\'i} and Kanis, Jakub and {\v Z}elezn{\'y}, Milo{\v s} and M{\"u}ller, Lud{\v e}k}, title = {Towards {Czech} on-line sign language dictionary -- technological overview and data collection}, pages = {41--44}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10043.html}, abstract = {In this article we present the current state of our work on an on-line sign language dictionary. The aim is to create both an explanatory and a translation dictionary. It is primarily targeted (but not limited) to the Czech and Czech sign language. At first we describe technological aspects of the dictionary and then our data collection practices. The dictionary is an on-line application build with respect to the linguistic needs. We use written text to represent spoken languages and several representations are supported for sign languages: videos, images, HamNoSys, SignWriting and interactive 3D avatar. To decrease time required for data collection and publishing in the dictionary we use computer vision methods for video analysis to detect sign boundaries and analyze the manual component of performed sign for automatic categorization. The content will be created by linguists using both new and already existing data. Then, the dictionary will be opened to the public with possibility to add, modify and comment data. We expect that this possibility of on-line elicitation will increase the number of informants, cover more regions and makes the elicitation cheaper and the evaluation easier. Furthermore we prepare a mobile interface of the dictionary. The mobile interface will use different format of web pages and different video compression methods optimized for slower Internet connection. We also prepare an offline version of the dictionary which can be automatically generated from the online content and downloaded for offline usage.} } @inproceedings{hruz:08013:sign-lang:lrec, author = {Hr{\'u}z, Marek and Campr, Pavel and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Semi-automatic Annotation of Sign Language Corpora}, pages = {78--81}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08013.html}, abstract = {The first step of automatic sign language recognition is feature extraction. It has been shown which features are sufficient for a successful classification of a sign. It is the hand shape, orientation of the hand in space, trajectory of the hands and the non-manual component of the speech (facial expression, articulation). Usually the efficiency of the feature extracting algorithm is evaluated by the rate of recognition of the whole system. This approach can be confusing since the researcher cannot be always sure which part of the system is failing. However if the corpora would be available with a detailed annotation of these features the evaluation would be more precise. A manual creation of the annotation data can be very time consuming. We propose a semi-automatic tool for annotating trajectory of head and hands and the shape of the hands. \par For the purpose of extracting the trajectory of hands a tracker is developed. In our case the tracker is based on similarity of the scalar description of objects. We describe the objects by seven Hu moments of the contour, a gray scale image (template), position, velocity, perimeter of the contour, area of the bounding box and area of the contour. For every new frame all objects in the image are detected and filtered. Every tracker computes the similarity of the tracked object and the evaluated object. As long as the tracker's certainty is above a threshold it is considered as ground truth. At this point all available data are collected from the object and saved as annotation. If the level of uncertainty is high, the user is asked to verify the tracking. \par If a perfect tracker was available all the annotation could be created automatically. But the trackers usually fail when an occlusion of objects occurs. Because of this problem the system must be able to detect occlusions of objects and have the user verify the resulting tracking. In our system we assume that the bounding box of an overlapped object becomes relatively bigger in the first frame of occlusion and relatively smaller in the first frame after occlusion. We consider the area of the bounding box as a feature which determines the occlusion. \par Up to now the annotation through tracker allows us to semi-automatically obtain the trajectory of head and hands and the shape of the hands. In the future we will extend the system to be able to determine the orientation of hands and combine it with a lip-reading system which we have ready for use. The obtained parameters can be then used as ground truth data for evaluation of feature extracting algorithm.} } @inproceedings{campr-etal-2008-collection:lrec, author = {Campr, Pavel and Hr{\'u}z, Marek and Trojanov{\'a}, Jana}, title = {Collection and Preprocessing of {C}zech {S}ign {L}anguage Corpus for Sign Language Recognition}, pages = {3175--3178}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1471}, abstract = {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. The corpus is mainly focused on feature extraction and isolated SLR rather than continuous SLR experiments.} }