Image processor, treatment system, and image processing method for determining a position of a point

摘要

According to an image processor of one embodiment, a first acquirer acquires a first perspective image of a target, which has a first resolution. A second acquirer acquires a second perspective image of the target, which has a second resolution. A first image generator generates first and second display images respectively from the first and second perspective images. The first and third display images have a third resolution lower than at least one of the first and second resolutions. A first point acquirer acquires first and second corresponding points respectively on the first and second display images. A first corrector searches, on the second perspective image, a second image similar to a first image on the first perspective image, the first image including the first corresponding point, and changes, on the second perspective image, a position of the second corresponding point to a position of the second image.

主权项

1. An image processor comprising circuitry configured to implement at least:
a first acquirer that acquires a first perspective image of a target viewed at a first time, the first perspective image having a first resolution; a second acquirer that acquires a second perspective image of the target viewed at a second time different from the first time, the second perspective image having a second resolution; a first image generator that generates first and second display images from the first and second perspective images respectively, the first and second display images having a third resolution lower than at least one of the first and second resolutions; a first point acquirer that acquires a first point in the first display image and a first corresponding point in the second display image; and a first corrector that searches, in the second perspective image, based at least on part on pixel values in the first image and the second image, for a second image with a highest similarity to a first image in the first perspective image, the first image including the first point, and the first corrector corrects the position of the first corresponding point according to positional relation between the first and the second images.