(a)



(b)
Figure 3: Histograms calculated from the image gray values 9a), and the from the co-occurrence matrix (b).

Number of pixels in the image	Error (%)
	Figure 2(c)	Figure 2(d)
4096	11.96	7.81

Table 1: Errors compared between the segmented images in Figure 2(c) and 2(d).
Another example illustrates the application of our algorithm to segmentation of remote -sensing multispectral images is given in Figure 4. A three near visible band image acquired by JERS -1 optical sensors was used, and shown in Figure 49a). Two threshold values obtained from our algorithm were 82 and 141, which result in segmenting the image into three classes and the result is shown in Figure 49b)

4. Conclusion
The gray-level co-occurrence matrix was used to produce a histogram that provides better results in the threshold selection process. A significant improvement by the algorithm presented was obtained and illustrated by using a synthetic image. Unsupervised classification of remote-sensing multispectral images is an application of such an algorithm.

(a)



(b)
Figure 4: Experiment using a JERS-1/OPS image. (a) Original image (b) Segmented image.
5. Acknowledgement
The authors wish to thank the National Research Council of Thailand (NRCT) for providing the satellite image data.
References

• Ahuja, N. and Rosefeld, A., 1978. A note on the use of second-order gray-level statistics for threshold selection. IEEE Trans. Systems, Man, and Cybernatics, SMC-8 912), pp. 895-898.
• Dulyakarn, P., Rangsanseri, Y., and Thitimajshima, P., 1999. Segmentation of multispectral images based on multithresholding. In: 2nd International Symposium on Operationalization of Remote Sensing.
• Jain, R., Katsuri, R., and Schunck, B.G., 1995. Machine Vision. McGraw-Hill International Editions, pp. 234-239.
• Otsu, N., 1979. A threshold selection method from gray-level histograms. IEEE Trans. Systems, Man, and Cybernetics, 9(1), pp. 62-66.
• Richards, J.A., 1994. Remote Sensing Digital Image Analysis. Springer-Verlag Publishing Company, Inc., pp. 133-144.
• Sahoo, P.K., Soltani, S., Wong, A.K.C., Chen, Y.C., 1988. A survey of thresholding techniques. Computer Vision, Graphics, and Image processing, 41, pp. 233-260.