An adaptive feature points selection algorithm based on image features of Digital Subtraction Angiography

Abstract

In the Digital Subtraction Angiography (DSA) image registration algorithm, the precision of the control points determines the accuracy of geometric correction and registration as well as their number and the distribution in image. Control points usually adopt the grid points. However, a more effective method is to ex-tract control points adaptively according to the image features. In this paper, a control point's selection algorithm of DSA images is proposed based on adaptive multi-scale vascular enhancement and error diffusion algorithm. The proposed algorithm can put the control points to positions of blood vessels adaptively, or to the other positions of the key image characteristics, and the proposed algorithm can optimize the number of control points according to practical needs, which will ensure the accuracy of DSA image registration.