Title :
A new method of SAR image segmentation based on neural network
Author :
XiaoRong, Xue ; Yanning, Zhang ; Rongchun, Zhao ; Feng, Duan ; Yi, Chen
Author_Institution :
Northwestern Polytech. Univ., Xi´´an, China
Abstract :
For the speckle consisted in SAR image, SR image cannot be segmented efficiently with traditional methods. In this paper, according to the features of SAR image and ANN, the automatic clustering method based on competitive Hopfield NN is used o segment SAR image. With experiment, it is proved that a good result can be gotten with the method proposed in the paper, and at the same time, the speckle in the SAR image is also reduced greatly.
Keywords :
Hopfield neural nets; image segmentation; speckle; synthetic aperture radar; Hopfield NN; SAR image; automatic clustering; image segmentation; neural network; speckle; Artificial neural networks; Clouds; Clustering methods; Computer vision; Histograms; Image segmentation; Neural networks; Object recognition; Speckle; Stochastic resonance;
Conference_Titel :
Computational Intelligence and Multimedia Applications, 2003. ICCIMA 2003. Proceedings. Fifth International Conference on
Print_ISBN :
0-7695-1957-1
DOI :
10.1109/ICCIMA.2003.1238116
