It is the basis of realization ship classification to accurately extract geometric parameters of the ship target in synthetic aperture radar(SAR) images. Due to the unique SAR imaging mechanism, azimuth ambiguity and sidelobe effects seriously impact on geometric parameters estimation of the ship target. Therefore, a method is presented to extract geometric parameters of the ship based on iterative linear regression. Firstly, the orientation of the goal spindle is extracted by linear regression. Then false target pixels are removed away from the ship spindle by iteration. Finally, the proposed method is verified with the actual measured SAR image. Experimental results show that the proposed algorithm has a better results of parameter estimation for high resolution SAR image of the ship target slice.