The Comparison of Classification Algorithms for Remote Sensing Images

Subject Areas : Electronics Engineering

najmeh  Cheraghi Shirazi ¹ (Islamic Azad University Bushehr Branch)
Roozbeh  Hamzehyan ² (Islamic Azad University Boushehr Branch)
Ashkan  Masoomi ³ (Islamic Azad University Ahram Branch)

Received: 2015-02-21 Accepted : 2016-04-12 Published : 2015-09-10

Keywords:

Abstract :

Although a large number of remote sensing image classification algorithm is proposed, but rarely performance of them are compared with each other. In this research, we classify satellite remote sensing images using two unsupervised classification algorithm and eight supervised classification algorithm which includes a number of common algorithms twenty years, tested and compared.  Our analysis focused on satellite images of the 12 spectral bands.  In comparison of these algorithms, the number of training samples is equated. These algorithms are compared with each other in terms of complexity, accuracy and reliability. The results show that accuracy of classification directly proportion to the number of training samples. The user can also choose efficient algorithms, depending on the complexity, accuracy and reliability of each parameter.

References:

1. Abend, K., and Harley, T. J. (1969) Comments "On the mean accuracy of statistical pattern recognisers". IEEE Transactions of Information Theory, May, 420-421.


2. Chapelle, O., Haffner, P., and Vapnik, V. N. (1999) Support vector machines for histogram-based image classification. IEEE Transactions on Neural Networks, 10, 1055-1064.


3. Huang, C., Davis, L. S., and Townshend, J. R. G. "An assessment of support vector machines for land cover classification." International Journal of Remote Sensing, (2002) 23, 725-749.


4. Tso, B. C. K., and Mather, P. M., (2001) Classification Methods for Remotely sensed Data. London: Taylor and Francis.


5. Wilkinson, G. G. (2000) Processing and classification of satellite images. Encyclopaedia of Analytical Chemistry, Edited by R. A. Meyers. John Wiley and sons, 8679-8693.


6. Zhu, G., and Blumberg, D. G., (2002) Classification using ASTER data and SVM algorithms; The case study of Beer Sheva, Israel. Remote Sensing of Environment, 80, 233-240.


7. N. Docquier, S. Candel, Combustion control and sensors: a review, Progress in Energy and Combustion Science, 28 (2002) 107-150