Method and apparatus for merging images into a composit image
First Claim
1. A method for merging a pair of overlapping two-dimensional (2D) images, said images being projections of a single three-dimensional (3D) scene, said method comprising:
- selecting at least four feature points in the 3D scene, finding the 2D coordinate of the points in both images corresponding to the selected feature points, the 2D coordinates being found with respect to original coordinate systems in the two images, translating the original coordinate systems of the two images in order to substantially minimize the average coordinate ranges of the 2D coordinates found, determining the parameters of a substantially optimal projective transformation relating the corresponding translated coordinates in the two image, determining the parameters of the projective transformation for application in the untranslated coordinate systems of the two images, and merging the two images by transforming one image according to the projective transformation and combining the transformed image with the other image.
1 Assignment
0 Petitions
Accused Products
Abstract
This invention includes apparatus and methods for merging of overlapping two-dimensional (2D) images which are formed by a image pick-up device as projections of a three-dimensional (3D) scene. In particular, the merging includes image registration by projective transformation of one of the 2D images, the transformation being derived from corresponding feature found in both images. In order to achieve improved accuracy and stability, the coordinates of the corresponding feature points are chosen or are translated so that, on average, the numerical ranges of coordinate values are minimized. Apparatus of the invention includes an appropriately configured image processor or computer with an attached image acquisition device, which in one embodiment, is a diagnostic x-ray apparatus.
-
Citations
13 Claims
-
1. A method for merging a pair of overlapping two-dimensional (2D) images, said images being projections of a single three-dimensional (3D) scene, said method comprising:
-
selecting at least four feature points in the 3D scene, finding the 2D coordinate of the points in both images corresponding to the selected feature points, the 2D coordinates being found with respect to original coordinate systems in the two images, translating the original coordinate systems of the two images in order to substantially minimize the average coordinate ranges of the 2D coordinates found, determining the parameters of a substantially optimal projective transformation relating the corresponding translated coordinates in the two image, determining the parameters of the projective transformation for application in the untranslated coordinate systems of the two images, and merging the two images by transforming one image according to the projective transformation and combining the transformed image with the other image. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
Specification