ABSTRACT
Sign language recognition (SLR) has spawned more and more interest in human--computer interaction (HCI) society. The major challenge that faces SLR recognition now is developing methods that will scale well with increasing vocabulary size with a limited set of training data for the signer independent application. The automatic SLR based on hidden Markov models (HMMs) is very sensitive to gesture's shape information that makes the accurate parameters of the HMM incapable of describing the uncertain distributions of the observations in gesture's features. This paper presents an extension of the HMMs using interval type-2 fuzzy sets to produce interval type-2 fuzzy HMMs to model uncertainties of hypothesis spaces. The advantage of this extension is that it can handle both the randomness and fuzziness of traditional HMM mapping. This system aspires to be a solution to the scalability problem, i.e. has real potential for application on a large vocabulary. Furthermore, does not rely on the use of data gloves or other means as input devices, and operates in isolated signer-independent modes. Experimental results show that the type-2 FHMM has a comparable performance as that of the FHMM but is more robust to the gesture variation.
- Ong, S., and Ranganath, S. 2005. Automatic sign language analysis: a survey and the future beyond lexical meaning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7, 6(Jun. 2005), 873--891. DOI=10.1109/TPAMI.2005.112.Google Scholar
- Su, M. 2000. A fuzzy rule-based approach to spatio-temporal hand gesture recognition. IEEE Transactions on Systems, Man and Cybernetics, 30, 2 (May 2000), 276--281. DOI=10.1109/5326.868448.Google Scholar
- Rekha, J., Bhattacharya, J., and Majumder, S. 2011. Hand gesture recognition for sign language: a new hybrid approach. In Proceedings of the International Conference on Image Processing, Computer Vision and Pattern Recognition (USA, 2011), 1--7. DOI= 10.1.1.217.9421.Google Scholar
- Doliotis, P., Athitsos, V., and Perantonis, S. 2012. Hand shape and 3D pose estimation using depth data from a single cluttered frame. In Proceedings of the International Symposium on Advances in Visual Computing (Greece, 2012), 148--158. DOI= 10.1007/978-3-642-33179-4_15.Google ScholarCross Ref
- Athitsos, V., and Sclaroff, S. 2003. Estimating 3d hand pose from a cluttered image. In Proceeding of the IEEE International Conferences on Computer Vision and Pattern Recognition (USA, 2003), 1--8. DOI= 10.1.1.14.262.Google Scholar
- Kong, W., and Ranganath, S. 2014. Towards subject independent continuous sign language recognition: a segment and merge approach. Pattern Recognition, 47, 3 (March 2014), 1294--1308. DOI=10.1016/j.patcog.2013.09.014.Google ScholarDigital Library
- Gaoa, W., Fanga, G., Zhaoa, D., and Chenb, Y. 2004. A Chinese sign language recognition system based on SOFM/SRN/HMM. Pattern Recognition, 37, 12 (Dec. 2004), 2389--2402. DOI= 10.1016/j.patcog.2004.04.008.Google Scholar
- Tataru, V., Vieriu, R., and Goras, L. 2010. On hand gestures recognition using hidden Markov models. Electronics and Telecommunications, 51, 3(June 2010), 29--32.Google Scholar
- Zenga, J., Xieb, L., and Liuc, Z.-Q. 2008. Type-2 fuzzy Gaussian mixture models. Pattern Recognition, 41, 12 (Dec. 2008) 3636--3643. DOI=10.1016/j.patcog.2008.06.006Google Scholar
- Kim, J., Park K., Bang W., and Bien Z. 2002. Continuous gesture recognition system for Korean sign language based on fuzzy logic and hidden Markova Model. In Proceedings of the IEEE International Conference on Fuzzy Systems, (USA, 2002), 1574--1579. DOI= 0.1109/FUZZ.2002.1006741.Google Scholar
- Anwar, R., Husain, F., Belaid, S., and Sher, M. 2010. HMM and fuzzy logic: a hybrid approach for online Urdu script-based languages' character recognition. Knowledge-Based Systems, 23, 8 (Aug. 2010), 914--923. DOI=10.1016/j.knosys.2010.06.007Google Scholar
- Sushmita, M., and Acharya, T. 2007. Gesture recognition: a survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 37, 3 (March 2007), 311--324. DOI= 10.1109/TSMCC.2007.893280.Google Scholar
- Gao, W., M a, J., and Wu, J. 2000. Sign language recognition based on HMM/ANN/DP. International Journal of Pattern Recognition and Artificial Intelligence, 4, 5(June 2000), 587--602. DOI= 10.1142/S0218001400000386.Google Scholar
- Christian, V., and Metaxas, D. 1999. Parallel hidden Markov models for American sign language recognition. In Proceedings of the Seventh IEEE International Conference on Computer Vision, (Greece, 1999), 116--122. DOI=10.1109/ICCV.1999.791206. Google ScholarCross Ref
- AL-Rousan, M., Assaleh, K., and Tala'a, A. 2009. Video-based signer-independent Arabic sign language recognition using hidden Markov models. Applied Soft Computing, 9, 3 (March 2009), 990--999. DOI= 10.1016/j.asoc.2009.01.002.Google Scholar
- Ibraheem, N., Hasan, M., Khan, R., and Mishra, P. 2012. Understanding color models: a review. Journal of Science and Technology, 2, 3(March 2012), 265--275. DOI=10.1.1.679.8051.Google Scholar
- Kumar, K., Ramakrishna, M., and Prasad, B. 2013. Feature extraction using sparse SVD for biometric fusion in multimodal authentication. International Journal of Network Security & Its Applications, 5, 4(April 2013), 83--94. DOI=10.5121/ijnsa.2013.5406. 83. Google ScholarCross Ref
- Zeng, J., and Liu, Z. 2006. Type-2 fuzzy hidden Markov models and their application to speech recognition. IEEE Transaction on Fuzzy Systems, 14, 3(March 2006), 454--467. DOI= 0.1109/TFUZZ.2006.876366.Google Scholar
- Zeng, J., and Qiang, L.2007. Type-2 fuzzy sets for pattern recognition: the state-of-the-art. Journal of Uncertain Systems, 1, 3 (January 2007), 163--177. DOI= 10.1007/978-3-662-44690-4_3Google Scholar
- Youssif, A., Aboutabl, A., and Ali, H. 2011. Arabic Sign language (ArSL) recognition system using HMM. International Journal of Advanced Computer System and Applications, 2, 11(Nov. 2011), 45--51. DOI=10.1.1.673.5705.Google Scholar
Recommendations
An algorithm on sign words extraction and recognition of continuous Persian sign language based on motion and shape features of hands
Sign language is the most important means of communication for deaf people. Given the lack of familiarity of non-deaf people with the language of deaf people, designing a translator system which facilitates the communication of deaf people with the ...
Towards subject independent continuous sign language recognition
This paper presents a segment-based probabilistic approach to robustly recognize continuous sign language sentences. The recognition strategy is based on a two-layer conditional random field (CRF) model, where the lower layer processes the component ...
Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning
Research in automatic analysis of sign language has largely focused on recognizing the lexical (or citation) form of sign gestures as they appear in continuous signing, and developing algorithms that scale well to large vocabularies. However, successful ...
Comments