ABSTRACT

Shu, J.; Chen, Z., and Xu, C., 2018. Feature segmentation for blurred edge of ship image based on depth learning. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 781–785. Coconut Creek (Florida), I SSN 0749-0208.

In traditional feature segmentation for blurred edge of ship image, geometric active contour model is often used, and it does not consider the global feature of ship image, which is easy to occur over segmentation phenomenon, resulting in longtime segmentation and inaccurate segmentation results. On the basis of deep learning, feature segmentation technique for blurred edge of ship image is proposed. Ship image is preprocessed to remove the impurities and noises in the image, and segment the blurred edge of the processed ship image. The experimental results show that the method can reduce the segmentation time of the blurred edge of ship image, and has high efficiency and accurate segmentation results.

This content is only available as a PDF.
You do not currently have access to this content.