Ma, G. and Wei, M., 2020. ASAR mesoscale ocean front image contour extracting method. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 947–951. Coconut Creek (Florida), ISSN 0749-0208.
When the current method is used to extract the contour of the ocean front image, it can not effectively remove the noise in the ocean front image. The extracted results are not consistent with the actual situation, and there are problems of poor denoising effect and low accuracy of the extracted results. The ASAR mesoscale extracting method of the ocean front image contour was proposed. The ocean front image was subjected to geometric correction during the pretreatment process, and the Contourlet transform was used to remove the noise in the ocean front image. The gray co-occurrence matrix was used to select gray co-occurrence matrix eigenvectors such as mean, variance, homogeneity and dissimilarity. The feature of the ocean front image contour was obtained by the above eigenvectors, and the contour of the ocean front image was extracted by its feature. The experimental results show that the proposed method has good denoising effect, high accuracy of extraction results.