Abstract
Many feature generation methods have been developed for object recognition. Some of these methods succeeded in achieving the invariance against object translation, rotation and scaling but faced problems of the bright background effect and non-uniform light on the quality of the generated features. This problem has objected recognition systems to work in free environment. This paper proposes a new method to enhance the features quality based on Pulse-Coupled Neural Network (PCNN). An adaptive model is proposed that defines continuity factor is as a weight factor of the current pulse in signature generation process. The proposed new method has been employed in a hybrid feature extraction model that is followed by a classifier and was applied and tested in Arabic Sign Language (ASL) static hand posture recognition; the superiority of the new method is shown.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ranganath, H.J., Kuntimad, G., Johnson, J.L.: Pulse Coupled Neural Networks for Image Processing. In: PCNN International Workshop, Huntsville, Alabama (April 5, 1995)
Eckhorn, R., Reitboeck, H.J., Arndt, M., Dicke, P.: Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex. Neural Computation 2(3), 293–307 (1990)
Zhang, D., Mabu, S., Hirasawa, K.: Image de-noising using pulse coupled neural network with an adaptive Pareto genetic algorithm. IEEJ Transactions on Electrical and Electronic Engineering 6(5), 474–482 (2011)
Johonson, J.L.: Pulse-Coupled Neural Nets: translation, rotation, scale, distortion, and intensity signal invariance for images. Appl. Opt. 33(26), 6239–6253 (1994)
McClurkin, J.W., Zarbock, J.A., Optican, L.M.: Temporal Codes for Colors, Patterns and Memories. In: Peters, A., Rockland, K.S. (eds.) Cerebral Cortex, vol. 10, p. 443. Plenum Press, NY (1994)
Ranganath, H.S., Kuntimad, G., Johnson, J.L.: Pulse coupled neural networks for image processing. In: Proceedings of Southeast Conference on Visualize the Future, Raleigh, pp. 37–43 (1995)
Abdel-Wahab, M.S., Abul-Ela, M., Samir, A.: Arbic Sign Langugae Recognition using Neural Network and Graph Matching Techniques. In: AIC 2006 Proceedings of the 6th WSEAS International Conference on Applied Informatics and Communications (2006)
Bauer, B., Hienz, H.: 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 (2000)
Tanibata, N., Shimada, N., Shirai, Y.: Extraction of Hand Features for Recognition of Sign Language Words. In: Proceedings of the 15th International Conference on Vision Interface, Calgary, Canada (2001)
Zieren, J., Kraiss, K.-F.: Robust Person-Independent Visual Sign Language Recognition. In: Proceedings of Pattern Recognition and Image Analysis, Second Iberian Conference, Estoril, Portugal (2005)
Kelly, D., McDonald, J., Markham, C.: Continuous recognition of motion based gestures in sign language. In: 2009 IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1073–1080 (2009)
Assaleh, K., Al-Rousan, M.: Recognition of Arabic Sign Language Alphabet Using Polynomial Classifiers. EURASIP Journal on Applied Signal Processing Society (13), 2136–2145 (2005)
El-Bendary, N., Zawbaa, H.M., Daoud, M.S., Hassanien, A.E., Nakamatsu, K.: ArSLAT: Arabic Sign Language Alphabets Translator. International Journal of Computer Information Systems and Industrial Management Applications 3, 498–506 (2011) ISSN 2150-7988
Forgá, R.: Feature Generation Improving by Optimized PCNN. In: 6th International Symposium on Applied Machine Intelligence and Informatics, SAMI 2008, January 21-22, pp. 203–207 (2008)
Ali, A.S., Hussien, A.S., Tolba, M.F., Youssef, A.H.: Visualization of large time-varying vector data. In: 3rd IEEE International Conference on Computer Science and Information Technology, art no. 5565176, pp. 210–215 (2010)
Khalifa, A.S., Ammar, R.A., Tolba, M.F., Fergany, T.: Dynamic online allocation of independent task onto heterogeneous computing systems to maximize load balancing. In: 8th IEEE International Symposium on Signal Processing and Information Technology, art. no. 4775659, pp. 418–425 (2008)
Tolba, M.F., Abdel-Wahab, M.S., Taha, I.A., Anbar, A.A.: Directed acyclic graphs scheduling in grid computing environments. In: International Conference on Internet Computing, pp. 260–266 (2004)
Khattab, D.R., El-Latif, Y.M.A., Wahab, M.S.A., Tolba, M.F.: Efficient face-based non-split connectivity compression for quad and triangle-quad meshes. In: 3rd International Conference on Computer Graphics Theory and Applications (GRAPP), pp. 31–38 (2008)
Fahmy Tolba, M., Saied Abdel-Wahab, M., Aboul-Ela, M., Samir, A.: Image Signature Improving by PCNN for Arabic Sign Language Recognition. Canadian Journal on Artificial Intelligence, Machine Learning & Pattern Recognition 1(1) (March 2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Elons, A.S., Aboull-Ela, M. (2012). Arabic Sign Language Recognition System Based on Adaptive Pulse-Coupled Neural Network. In: Hassanien, A.E., Salem, AB.M., Ramadan, R., Kim, Th. (eds) Advanced Machine Learning Technologies and Applications. AMLTA 2012. Communications in Computer and Information Science, vol 322. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35326-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-35326-0_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35325-3
Online ISBN: 978-3-642-35326-0
eBook Packages: Computer ScienceComputer Science (R0)