Novel Feature Extraction and Classification Technique for Sensor-Based Continuous Arabic Sign Language Recognition

详细信息    查看全文

• 关键词：Sign language recognition ; Feature extraction ; Sensor ; based gloves ; Pattern classification
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9492
• 期：1
• 页码：290-299
• 全文大小：449 KB
• 参考文献：1.Shanableh, T., Assaleh, K.: User-independent recognition of Arabic sign language for facilitating communication with the deaf community. Digit. Signal Process. 21, 535–542 (2011)CrossRef
  2.Assaleh, K., Shanableh, T., Zourob, M.: Low complexity classification system for glove-based arabic sign language recognition. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds.) ICONIP 2012, Part III. LNCS, vol. 7665, pp. 262–268. Springer, Heidelberg (2012)CrossRef
  3.Mohandes, M., Deriche, M., Liu, J.: Image-based and sensor-based approaches to arabic sign language recognition. IEEE Trans. Hum. Mach. Syst. 44, 551–557 (2014)CrossRef
  4.Mohandes, M., A-Buraiky, S., Halawani, T., Al-Baiyat, S.: Automation of the Arabic sign language recognition. In: Proceedings of the 2004 International Conference on Information and Communication Technologies: From Theory to Applications, pp. 479–480 (2004)
  5.Tubaiz, N., Shanableh, T., Assaleh, K.: Glove-based continuous Arabic sign language recognition in user-dependent mode. IEEE Trans. Hum. Mach. Syst. PP(99), 1–8 (2015). doi:10.​1109/​THMS.​2015.​2406692
  6.Oz, C., Leu, M.C.: American sign language word recognition with a sensory glove using artificial neural networks. Eng. Appl. Artif. Intell. 24, 1204–1213 (2011)CrossRef
  7.Kong, W.W., Ranganath, S.: Towards subject independent continuous sign language recognition: a segment and merge approach. Pattern Recogn. 47, 1294–1308 (2014)CrossRef
  8.Gao, W., Fang, G., Zhao, D., Chen, Y.: A Chinese sign language recognition system based on SOFM/SRN/HMM. Pattern Recogn. 37, 2389–2402 (2004)CrossRef MATH
  9.Sharjah City for Humanitarian Services (SCHS). http://​www.​schs.​ae/​indexs.​aspx
  10.Assaleh, K., Shanableh, T., Fanaswala, M., Amin, F., Bajaj, H.: Continuous Arabic sign language recognition in user dependent mode. J. Intell. Learn. Syst. Appl. 2, 19–27 (2010)
  11.Starner, T., Weaver, J., Pentland, A.: Real-time American sign language recognition using desk and wearable computer based video. IEEE Trans. Pattern Anal. Mach. Intell. 20(12), 1371–1375 (1998)CrossRef
  
• 作者单位：Mohammed Tuffaha (17)
  Tamer Shanableh (17)
  Khaled Assaleh (18)
  
  17. Department of Computer Science and Engineering, American University of Sharjah, Sharjah, UAE
  18. Department of Electrical Engineering, American University of Sharjah, Sharjah, UAE
  
• 丛书名：Neural Information Processing
• ISBN：978-3-319-26561-2
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

This paper proposes a novel approach to continuous Arabic Sign Language recognition. We use a dataset which contains 40 sentences composed from 80 sign language words. The dataset is collected using sensor-based gloves. We propose a novel set of features suitable for sensor readings based on covariance, smoothness, entropy and uniformity. We also propose a novel classification approach based on a modified polynomial classifier suitable for sequential data. The proposed classification scheme is modified to take into account the context of the feature vectors prior to classification. This is achieved through the filtering of predicted class labels using median and mode filtering. The proposed work is compared against a vision-based solution. The proposed solution is found to outperform the vision-based solution as it yields an improved sentence recognition rate of 85 %.