SAR Ship Image Segmentation Based on FCM Straight Line Fitting and Radon Transform
HE Shun
LI Danyang
LIU Xiangxi
Abstract：Aiming at the problem that synthetic aperture radar(SAR)ship image segmentation results lose ship geometry fea-tures,a new segmentation method of SAR ship image based on FCM line fitting and Radon transform is proposed.Firstly,the im-proved fuzzy C-means clustering algorithm is used to initially segment the ship target and the ocean background,and then the mini-mum distance linear fitting of the segmentation results is carried out to obtain the ship target's azimuth angle,and then the image is segmented by Radon transform.Finally,morphological optimization is carried out on the image after Radon transform.The experi-mental results show that compared with the traditional segmentation algorithm,the difference between the algorithms can be in-creased to 0.996 060.Intra-domain consistency is increased to 0.679 505.The shape complexity is reduced to 1.990 942,which can effectively improve the segmentation effect of SAR ship target and enhance the stability of ship target segmentation,which is of great significance for the recognition and classification of Marine ship target.
Keywords：synthetic aperture radarimage segmentationship targetstraight line fittingRadon transform
Publication Date：2025-02-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 39-44,93 )