Study on the classification of multi-spectral images based on a FSVM multi-class classifier with the binary tree

Abstract

Due to the features of the multi-spectral images, the result with the usual methods based on the support vector machine (SVM) and binary tree is not satisfactory. In this paper, a fuzzy SVM multi-class classifier with the binary tree is proposed for the classification of multi-spectral images. The experiment is conducted on a multi-spectral image with 6 bands which contains three classes of terrains. The experimental results show that this method can improve the segmentation accuracy.

Keywords

Binary Tree / Optimal Hyperplane / Remote Sensing Symposium / High Resolution Satellite Image / Fuzzy Factor

References

[1] ZhangJ.-s., HeC.-y., PanY.-z., LiJ.. Journal of Remote Sensing, 2006, 10: 49

[2] Yifan Zhang, Mingye He and Muyun Weng, 1st IEEE Conference on Industrial Electronics and Applications, 1 (2006).

[3] ZengM., ZhangJ.-x., WangX.-h.. Journal of Optoelectronics·Laser, 2006, 17: 275

[4] ZhengZ., ZhangY.-x., HuY.-x.. Journal of Optoelectronics·Laser, 2007, 18: 491

[5] Peijun Li and Hongtao Hu, IEEE International Geoscience and Remote Sensing Symposium 1481 (2007).

[6] ShuyuY., JianglingG.. 16th IEEE Symposium on Computer-Based Medical Systems, 2003, 2: 68

[7] VapnikV.N.. Statistical Learning Theory, 1998, New York, Wiley

[8] M. Pontil and A. Verri, Massachusetts Inst. Technol., AI Memo, 1997.

[9] LiuS.-y., DuZ.. CAAI Transactions on Intelligent Systems, 2007, 2: 30