Shape Classification Using Multiple Classifiers with Different Feature Sets

Abstract:

In this paper, a new shape classification method based on different feature sets using multiple classifiers is proposed. Different feature sets are derived from the shapes by using different extraction methods. The implements of feature extraction are based on two ways: Fourier descriptors and Zernike moments. Multiple classifiers comprise Normal densities based linear classifier, k-nearest neighbor classifier, Feed-Forward neural network, Radial Basis Function neural network classifier. Each classifier is trained by two feature sets respectively to form two classification results. The final classification results are a combined response of the individual classifier using six different classifier combination rules and the results were compared with those derived from multiple classifiers based on the same feature sets and individual classifier. In this study we examined the different classification tasks on Kimia dataset. For the tasks the best combination strategy was found using the product rule, giving an average recognition rate of 95.83%.

• Periodical: Advanced Materials Research (Volumes 368-373)
• Pages: 1583-1587
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.368-373.1583
• Online since: October 2011
• Authors: Jun Ying Chen, Jing Chen, Zeng Xi Feng
• Keywords: Feature Set, Multiple Classifier, Shape Classification

References

[1] K Wall and PE Danielsson: Computer Vision, Graphics, and Image Processing (1984), pp.220-227.

[2] Baruch O. and Murray H.L.: Pattern Recognition (1988), pp.581-589.

[3] S.R. Dubois and F.H. Glanz: IEEE Trans. Pattern Anal. Machine Intell. 8:55-66 (1986).

[4] Zahn C.T. and Roskies R.Z.: IEEE Transactions on Computers, C-21:269-281(1972).

[5] Costa L. da F. and Sandler M.B.: Pattern Recognition Letters, 10(5):329-334(1989).

[6] Kim W.Y.; Kim Y.SA: Signal Processing: Image Communication, 16(1): 95-102(2000).

[7] Duda, R.O., Hart, P.E., and Stork, D.G. Pattern Classification, 2d Edition Wiley, New York (2001).

[8] Xu, L.; Krzyzak, A.; Suen, C.Y.; and C. Y. Suen.:IEEE Transactions on Systems, Man and Cybernetics, 23(3):418–435(1992).

DOI: 10.1109/21.155943

[9] K Chen, L Wang and HS Chi.: International Journal of Pattern Recognition and Artificial Intelligence, 11(3): 417-445(1997).

[10] ZQ Zhao, DS Huang and BY Sun.: Pattern Recognition Letters (2004).

[11] J Kittler, M. Hatef, R. P. W Duin and J. Matas.: IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(3):226–239(1998).

DOI: 10.1109/34.667881

[12] Partridge, D.: Neural Networks 9: 263-271(1996).

[13] S.Jeannin and M.Bober. Technical Report ISO/IEC JTC 1/SC 29/WG 11 MPEG99/N2690, MPEG-7, Seoul (1999).

[14] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner. Gradient-based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11): 2278-2324(1998)

DOI: 10.1109/5.726791