Recognition of Isolated Words of the Polish Sign Language
The paper considers recognition of isolated words of the Polish Sign Language using a canonical stereo system that observes the signer from a frontal view. Recognition is based on human skin detection and Hidden Markov Models. Several feature vectors taking into account information about the hand shape and 3D position of the hand with respect to the face are examined. To improve the recognition rate the classifiers are combined by voting or by fuzzy integral. We focus on 101 words that can be used at the doctor’s and at the post office.
Unable to display preview. Download preview PDF.
- 3.Grobel K, Assam M (1997) Isolated Sign Language Recognition Using Hiden Markov Models. Proc. of the IEEE Int. Conf. on SMC, Orlando:162–167Google Scholar
- 4.Hendzel J K (1997) Dictionary of the Polish Sign Language. OFFER Press, Olsztyn (in Polish)Google Scholar
- 5.Kapuscinski T, Wysocki M (2003) Vision-Based Recognition of Polish Sign Language. Proceedings of the Symposium on Methods of Artificial Intelligence AI-METH, Gliwice, Poland:145–148Google Scholar
- 6.Konolige K (1997) Small Vision System: Hardware and Implementation. Proc. of the Int. Symp. on Robotic Research, Hayama, Japan:111–116Google Scholar
- 7.Marnik J, Wysocki M (2004) Hand Posture Recognition Using Mathematical Morphology. Archives of Theoretical and Applied Informatics, 16,4:279–293Google Scholar
- 8.Pavlovic V I, Sharma R, Huang T S (1997) Visual Interpretation of Hand Gestrures for Human-Computer Interaction: A Review. IEEE Trans PAMI, 197:677–693Google Scholar
- 10.Starner T, Weaver J, Pentland A (1998) Real-time American Sign Language Recognition Using Desk and Wearable Computer Based Video. IEEE Trans. PAMI, 20,12:1371–1375Google Scholar
- 11.Suszczanska N, Szmal P, Francik J (2002) Translation Polish Text into Sign Language in the TGT System. Proc. of the 20th IASTED International Multi-conference Applied Informatics, Insbruck:282–287Google Scholar
- 13.Theodoridis S, Koutroumbas K (1999) Pattern Recognition. Acad. Press, New YorkGoogle Scholar
- 14.Young S et al. (2000) The HTK Book. Microsoft CorporationGoogle Scholar