Study on the Optimal Image Resolution for Image Segmentation

Abstract:

Resolution is one of the basic and key indexes on assessing the quality of remote sensing image. However, it can not be concluded that the higher the image resolution, the better the segmentation result, since high resolution image contains not only more details of interested object, but also more redundant information of background which causes much difficulty on image segmentation and target recognition. To determine an optimal image resolution for image segmentation, an image pyramid with resolution continuously changing is built by down sampling and super-resolution techniques at first, and then an index called degree of image segmentation is presented based on the image histogram. Degree of image segmentation is a hybrid index which is designed based on integrating the area and symmetry of the valley of the image histogram. At last the optimal image resolution is determined by seeking the maximum value of degree of image segmentation from the images with different resolutions contained in the image pyramid. The experimental results illustrate that degree of image segmentation is directly related with the result of segmentation, and the degree of image segmentation presented in this paper is a good index to describe how well an image can be segmented in the viewpoint of quantitative and qualitative assessing.

• Periodical: Applied Mechanics and Materials (Volume 665)
• Pages: 724-732
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.665.724
• Online since: October 2014
• Authors: Yan Tian, Chong Wu Ruan*, Chen Hong Sui
• Keywords: Image Pyramid, Image Segmentation, Image Segmentation Degree, Optimal Image Resolution

References

[1] Puech C., 1994, Thresholds of homogeneity in targets in the landscape-relationship with remote sensing, International Journal of Remote Sensing 75(21), 2421-2435.

DOI: 10.1080/01431169408954255

[2] Bian L., 1997, Multiscale nature of spatial data in scaling up environmental models, Chap. 1 in Scale in Remote Sensing and GIS, Quattrochi D. A. and Goodchild M. F. (Eds. ), Lewis Publishers, New York, pp.13-26.

DOI: 10.1201/9780203740170-2

[3] Dubayah R. and Wood E. F., 1997, Multiscaling analysis in distributed modeling and remote sensing: an application using soil moisture, Chap. 5 in Scale in Remote Sensing and GIS, Quatrocchi D. A. and Goodchild M., (Eds)., Lewis Publishers, New York, pp.93-112.

DOI: 10.1201/9780203740170-6

[4] Weissel J. K., Partson L. F., and Malinverno A., 1994, The length-scaling properties of topography, Journal of Geophysical Research 99, 13997-14012.

DOI: 10.1029/94jb00130

[5] Adjali I. and Appleby S., 2001, The multifractal structure of the human population distribution, Chap. 4 in Modelling Scale in Geographical Information Science, Nicholas J. T. and Peter M. A., (Eds. ), John Wiley &Sons, pp.69-86.

[6] Gu Y. F., Zhang Y., and Zhang J. P., 2002, Multiresolution remote sensing image fusion based on the normalized correlation moment, Journal of Image and Graphics 7a(11), 1220-1224.

[7] Ali Z., Hussain S., and Kernel I. A., 2005, Kernel based robust object tracking using model updates and Gaussian pyramids, Proceedings of the IEEE Symposium on Emerging Technologies, 144-150.

DOI: 10.1109/icet.2005.1558870

[8] Gluckman J., 2006, Scale variant image pyramids, Proc. IEEE Conf. Computer Vision Patt. Recog., 1, 1069-1075.

[9] Pan F. Z. and Zhang L. M., 2004, Super-resolution of images based on restoration of residual errors by neural networks, ACTA ELECTRONICA SINICA 1(32), 161-165.

[10] Zhang Y J, 2001, Image Segmentation, first ed. Science Press, Beijing.

[11] Shafer G., 1976, A Mathematical Theory of Evidence, first ed. Princeton University Press, New Jersey.

[12] Otsu N., 1979, A Threshold Selection Method from Gray-Level Histograms, IEEE Trans. Systems, Man, and Cybernetics, SMC-9(1), 62-66.

DOI: 10.1109/tsmc.1979.4310076