Abstract
In the application of face recognition, with the increasing number of stored face mode in ART2 network, it will spend a lot of time to learn or identify the future entering mode of ART2 network, and then the speed of face recognition will become slower. The author proposed an improved ART2 algorithm based on rough classification, using the adaboost algorithm to train a classifier to determine whether the face wearing glasses, the face mode will be divided into two categories of people who wear glasses and do not wear glasses by deciding a people whether to wear glasses. The experiments show that the method can greatly improve the speed of face recognition.
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
Li, F., Zhan, J.: Fuzzy adapting vigilance parameter of ART-II neural nets. In: IEEE International Conference on Neural Networks, pp. 1680–1685. IEEE, New York (1994)
Carpenter, G.A., Grossberg, S.: A massively parallel architecture for a self-organizing neural pattern recognition machine. Comp. Vision Graphics and Image Process 37(1), 54–115 (1987)
Carpenter, G.A., Grossberg, S.: ART-2: self-organization of stable category recognition codes for analog input pattern. App. Optics 26(23), 4919–4930 (1987)
Carpenter, G.A., Grossberg, S.: ART-3: hierarchical search using chemical transmitters in self-organizing pattern recognition architectures. Neural Networks 3(2), 129–152 (1990)
Gu, M., Ge, L.: Improvements of ART2 neural network based on amplitude component. Computer Engineering and Applications 43(13), 52–54 (2007)
Whiteley, J.R., Davis, J.F., Mehrotra, A., et al.: Observations and Problem Applying ART2 for Dynamic Sensor Patter Interpretation. IEEE Trans. on Systems, Man and Cybernetics 26(4), 423–437 (1996)
Qian, X., Wang, Z., Wang, Y.: A Method of Data Clustering Based on Improved Algorithm of ART2. In: Proc. of the 4th International Conference on Machine Learning and Cybernetics, Guangzhou, China, pp. 2021–2026 (2005)
Ma, J.: A new ART2 neural network model. Pattern Recognition and Artificial Intelligence 13(2), 231–234 (2000)
Zhang, M., Guo, D.: The Improvement on ART-2 Neural Network Algorithm for Pattern Recognition. Control Theory and Applications 17(1), 136–138 (2000)
Xu, Y., Ning, X., Huang, X.: The Research on a Fractionizing and Fitting ART2 Neural Network with Supervise. Acta Electronica Sinica (10), 1754–1756 (2004)
Ye, X.: Research of application of ART2 network with memory strength. Beijing University of Chemical Technology, pp. 51–56 (2011)
Dai, X., Lin, X.: An Artificial Neural Network Model by Introducing Memorizing-forgetting Mechanism. Beijing Institute of Petrochemical Technology 18(3), 1–6 (2010)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the IEEE Computer Society Conference on Computer Vision a Pattern Recognition, Kauai, Hawaii, pp. 511–518 (2001)
Guo, L., Wang, R.: Pedestrian Detection Method Based on Adaboost Algorithm. Computer Engineering 34(3), 202–204 (2008)
Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. IEEE ICIP (1), 900 (2002)
Viola, P.: Robust Real-time Object Detection. International Journal of Computer Vision 57(2), 137–154 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, M., Lin, X. (2013). The ART2 Neural Network Based on the Adaboost Rough Classification. In: Tan, T., Ruan, Q., Chen, X., Ma, H., Wang, L. (eds) Advances in Image and Graphics Technologies. IGTA 2013. Communications in Computer and Information Science, vol 363. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37149-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-37149-3_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37148-6
Online ISBN: 978-3-642-37149-3
eBook Packages: Computer ScienceComputer Science (R0)