Abstract
Many previous researchers have tried developing sign languages recognition systems in general and Arabic sign language specifically. They succeeded to achieve acceptable results for isolated gestures level, but none of them investigated the recognition of connected sequence of gestures. This paper focuses on how to recognize real-time connected sequence of gestures using graph-matching technique, also how the continuous input gestures are segmented and classified. Graphs are a general and powerful data structure useful for the representation of various objects and concepts. This work is a component of a real-time Arabic Sign Language Recognition system that applied pulse-coupled neural network for static posture recognition in its first phase. This work can be adapted and applied to different sign languages and other recognition problems.
Similar content being viewed by others
References
Doner B (1993) Hand shape identification and tracking for sign language interpretation. Looking at People Workshop, Chambery
Bauer B, Hienz H (2000) Relevant features for video-based continuous sign language recognition. In: Proceedings of the fourth IEEE international conference on automatic face and gesture recognition, pp 64–75
Chao M-W, Lin C-H, Chang C–C, Lee T-Y (2011) A graph-based shape matching scheme for 3D articulated objects. Comput Animat Virtual Worlds 22(2–3):295–305
Gupta M (2011) Design pattern mining using greedy algorithm for multi-labelled graphs. Int J Inf Commun Technol 3(4):314–323
Bauer B, Hienz H (2000) Relevant features for video-based continuous sign language recognition. In: Proceedings of the fourth IEEE international conference on automatic face and gesture recognition, pp 64–75
Tanibata N, Shimada N, Shirai Y (2001) Extraction of hand features for recognition of sign language words. In: Proceedings of the 15th international conference on vision interface. Calgary, Canada
Chen F-S, Fu C-M, Huang C-L (2003) Hand gesture recognition using a real-time tracking method and hidden Markov models. Image Vis Comput 21:745–758
Zieren J, Kraiss K-F (2004) Non-intrusive sign language recognition for human-computer interaction. In: 9th IFAC/IFIP/IFORS/IEA symposium analysis, design, and evaluation of human-machine systems, Atlanta, GA, pp 221–228
Zieren J. Kraiss, K-F (2005) Robust person- independent visual sign language recognition, proceedings of pattern recognition and image analysis, second Iberian conference, Estoril, Portugal
Dreuw P, Forster J, Gweth Y, Stein D, Ney H, Martínez G, Vergés-Llahí J, Crasborn O, Ormel E, Du W, Hoyoux T, Piater J, Moya JM, Wheatley M (2010) SignSpeak understanding, recognition, and translation of sign languages. In: 4th Workshop on the representation and processing of sign languages: corpora and sign language technologies, language resources and evaluation conference (LREC)
Al-Rousan M, Aljarrah O, Hussain M (2001) Automatic recognition of arabic sign language finger spelling. Int J Comput Their Appl 8(2):80–88 (Issue 1076-5204)
Jarrah O, Halawani A (2001) Recognition of gestures in Arabic Sign Language using neuro-fuzzy systems. Artif Intell, pp 117–138
Assaleh K, Al-Rousan M (2005) Recognition of Arabic sign language alphabet using polynomial classifiers. EURASIP J Appl Signal Process Soc 13:2136–2145
Mohandes M, Deriche M (2005) Image based Arabic sign language recognition. Signal processing and its applications, 2005. In: Proceedings of the eighth international symposium, vol 1, pp 86–89
Tolba MF, Abdellwahab MS, Abulle-Ela M, Samir A (2010) Image signature improving by PCNN for Arabic sign language recognition. Can J Artif Intell Mach Learn Pattern Recogn 1(1):1–6
Official Microsoft Xbox website, introduction of Kinect, http://www.xbox.com/en-US/kinect
Countdown to Kinect: 17 Controller-Free Games Launch in November. Microsoft News Center, https://www.microsoft.com/presspass/press/2010/oct10/10-18mskinectuspr.mspx
Kinect Fact Sheet, Microsoft News Center, June 2010, http://www.microsoft.com/presspass/presskits/xbox/docs/KinectFS.docx
Integrating Speech and Hearing Challenge Individuals. YouTube channel of Dr. Natheer Khasawneh, http://www.youtube.com/user/knatheer#p/a/u/1/vVL398dUU5Q
Topouzelis K, Karathanassi V, Pavlakis P, Rokos (2003) A neural network approach to oil spill detection using SAR data. In: 54th International astronautical congress, Bremen, Germany
Ma YD, Li L, Wang YF (2006) The principles of pulse coupled neural networks and its application. Science Press, Beijing
Eckhorn R, Reitboeck HJ, Arndt M, Dicke P (1990) Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex. Neural Comput 2(3):293–307
Forgá R (2008) Feature generation improving by optimized PCNN, applied machine intelligence and informatics. SAMI 2008. In: 6th International symposium, pp 203–207, Issue, 21–22, Jan. 2008
Kinser JM, Nguyen C (2000) Pulse image processing using centripetal autowaves. Proc SPIE 4052:278–284
Qiu H, Hancock ER (2003) Graph partition for matching. In: Proceedings of 4th international workshop on graph-based representations in pattern recognition. Springer LNCS2726, Berlin, pp 178—189
Delalandre M, Trupin E, Ogier JM (2004) Local structural analysis: a primer. In: Proceedings of workshop on graphics recognition. Springer, LNCS3088, Berlin, pp 220–231
Qiu H, Hancock ER (2003) Graph partition for matching. In: Proceedings of 4th international workshop on graph-based representations in pattern recognition. Springer LNCS2726, Berlin, pp 178–189
Messmer BT, Bunke H (1999) A decision tree approach to graph and subgraph isomorphism detection. Pattern Recogn 32(12):1979–1998
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tolba, M.F., Samir, A. & Aboul-Ela, M. Arabic sign language continuous sentences recognition using PCNN and graph matching. Neural Comput & Applic 23, 999–1010 (2013). https://doi.org/10.1007/s00521-012-1024-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-1024-0