Research On The Method Of Feature Point Extraction In Digital Image

Feature points extraction of digital image is a basic problem and a hot issue in the field of digital image processing,it has been widely used in image registration,video understanding,3D reconstruction,panorama stitching and other fields.The research on the method of feature points extraction in digital image has the high value both in academic and practical fields.Aimed at the research of the digital image feature point extraction algorithm,the main work of this paper is as follows:(1)This paper briefly introduces the significance and research status of the research on the method of feature points extraction in digital image,and also introduces the commonly used feature points extraction methods as well as Radon transform and Hough transform,Radon transform and Hough transform are the theoretical basis of feature point extraction algorithm proposed in this paper;(2)Based on Radon transform and Hough transform,this paper propose a new method to extract digital image corner points that can accurate locate corner points in digital image,and also has a good robustness against image additive noise;(3)Inspired by the Radon transform theory,this paper put forward a new method for extracting Blob points in digital image,and experiment results show that this method can quickly and accurately locate the position of Blob points in digital image and has strong robustness to additive noise.