Abstract
A multi-class classifier-based AdaBoost algorithm for the efficient classification of multi-class data is proposed in this paper. The traditional AdaBoost algorithm is basically a binary classifier and it has limitations when applied to multi-class data problems even though its multi-class versions are available. In order to overcome the problems of the AdaBoost algorithm for multi-class classification problems, we devise a AdaBoost architecture with its training algorithm that uses multi-class classifiers for its weak classifiers instead of series of binary classifiers. The proposed AdaBoost architecture can save its training time drastically and obtain more stable and more accurate classification results than a typical multi-class AdaBoost architecture based on binary weak classifiers. Experiments on an image classification problem with collected satellite image database are preformed. The results show that the proposed AdaBoost architecture can reduce its training time 50%- 70% depending on the number of training rounds while maintaining its classification accuracy competitive when compared to Adaboost.M2.
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
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Int. Conf. ICCVPR, vol. 1, pp. 511–518 (2000)
Freund, Y., Schapire, R.: A Decision -Theoretic Generalization of On-Line Learning and an Application to Boosting. In: Vitányi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23–37. Springer, Heidelberg (1995)
Schapire, R.: Using output codes to boost multiclass learning problems. In: Proc. of ICML, pp. 313–321 (1997)
Park, D.-C.: Partitioned Feature-based Classifier Model. In: Proc. of ISSPIT, vol. 1, pp. 412–417 (2009)
Kohonen, T.: The Self-Organizing Map. Proceedings of the IEEE 78, 1464–1480 (1990)
Park, D.-C.: Centroid Neural Network for Unsupervised Competitive Learning. IEEE Trans. Neural Networks 11(2), 520–528 (2000)
Kim, T.-H., Park, D.-C.: Multiclass-based AdaBoost Algorithm. Jouranl of IEEK 48CI-1 6, 44–50 (2011)
Park, D.-C., Kwon, O., Chung, J.: Centroid Neural Network with a Divergence Measure for GPDF Data Clustering. IEEE Trans. Neural Networks 19(6), 948–957 (2008)
Paschos, G.: Perceptually uniform color spaces for color texture analysis: an empirical evaluation. IEEE Trans. Image Processing 10(6), 932–937 (2001)
Ma, J.: Content-Based Image Retrieval with HSV Color Space and Texture Features. In: Proc. of Int. Conf. on , pp. 61–63 (2009)
Lam, E.Y., Goodman, J.W.: A mathematical analysis of the DCT coefficient distributions for images. IEEE Trans. on Image Processing 9(10), 1661–1666 (2000)
Li, H., Liu, G., Zhang, Z.: A new texture generation method based on pseudo-DCT coefficients. IEEE Trans. on Image Processing 15(5), 1300–1312 (2006)
Masi, S., Malik, J.: Object detection using a max-margin Hough transform. In: Proc. IEEE Int. Conf. CVPR, pp. 1038–1045 (2009)
Chang, T., Kuo, C.: Texture Analysis and Classification with Tree-Structured Wavelet Transform. IEEE Trans. on Image Processing 2(4), 429–441 (1993)
Wang, Z., Yong, J.: Texture analysis and classification with linear regression model based on wavelet transform. IEEE Trans. on Image Processing 17(8), 1421–1430 (2008)
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
Kim, TH., Park, DC., Woo, DM., Jeong, T., Min, SY. (2012). Multi-class Classifier-Based Adaboost Algorithm. In: Zhang, Y., Zhou, ZH., Zhang, C., Li, Y. (eds) Intelligent Science and Intelligent Data Engineering. IScIDE 2011. Lecture Notes in Computer Science, vol 7202. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31919-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-31919-8_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31918-1
Online ISBN: 978-3-642-31919-8
eBook Packages: Computer ScienceComputer Science (R0)