IP Library › Granted Patent US 12664670
Granted Patent B2
US 12664670 · App. 19/103,232 · Granted Jun 23, 2026

Method and system for automatic determination of registration accuracy

Inventors: Jared Rosenblum (Long Branch, NJ); Vikram Chandrashekhar (Trabuco Canyon, CA); Vibhu Chandrashekhar (Trabuco Canyon, CA)
Assignee: NeuroSimplicity, LLC
G06T7/38G06T7/337G06T2207/10016
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12664670
App. No.
19/103,232
Granted
Jun 23, 2026
Kind
B2
Abstract

Automatic determination of registration accuracy between a first image of a first object and a second image of the first object. Identifying a first image element in the first object by scanning the first image sequentially by image unit, and identifying a second image element in the first object by scanning the second image sequentially by the image unit. Registering the first image element to the second image element in a shared background coordinate space. Determining an accuracy of the registering by relating the first image element and the second image element to the shared background coordinate space, calculating a first distance between the first image element and a nearest point in the shared background coordinate space, and calculating a second distance between the second image element and the nearest point in the shared background coordinate space. Calculating a difference between the first distance and the second distance.

Claims (47)

1 . A method for automatic determination of registration accuracy between a first image of a first object and a second image of a second object, comprising:

identifying a first image element in the first object by scanning the first image sequentially by image unit;

identifying a second image element in the second object by scanning the second image sequentially by the image unit;

registering the first image element to the second image element in a shared background coordinate space;

determining an accuracy of the registering by relating the first image element and the second image element to the shared background coordinate space, calculating a first distance between the first image element and a nearest point in the shared background coordinate space, calculating a second distance between the second image element and the nearest point in the shared background coordinate space, and calculating a difference between the first distance and the second distance,

wherein

the first image and the second image are two-dimensional;

the image unit is a pixel;

the scanning of the first image sequentially is circling from a first perimeter of the first image inward; and

the scanning of the second image sequentially is circling from a second perimeter of the second image inward.

2 . The method of claim 1 , further comprising identifying an amount of deformation of the second object required to make the second object match the first object.

3 . The method of claim 1 , wherein:

the scanning of the first image sequentially is row by row; and

the scanning of the second image sequentially is row by row.

4 . The method of claim 1 , further comprising repeating the steps of the method for further first image elements and further second image elements.

5 . The method of claim 4 , wherein the registering of the first image element to the second image element in the shared background coordinate space comprises registering the further first image elements to the further second image elements in the shared background coordinate space, and minimizing a sum of the difference between the first distance and the second distance and further differences between further first distances and further second distances.

6 . The method of claim 1 , wherein the registering includes the process of calculating a transformation that aligns two or more image elements, objects, images, and/or coordinate spaces to each other.

7 . The method of claim 1 , wherein the shared background coordinate space is a coordinate space of the first image, the second image, a third unrelated space, or a fourth space that is a result of the registration.

8 . The method of claim 1 , wherein the first object is the same type as the type of the second object.

9 . The method of claim 1 , wherein the first image element is the same type as the type of the second image element.

10 . The method of claim 1 , wherein the first object is the same object as the second object.

11 . The method of claim 1 , wherein the first image element is the same image element as the second image element.

12 . The method of claim 1 , wherein an output of the accuracy determination is graphical or numerical.

13 . The method of claim 1 , where in the registering occurs before or after the identifying steps.

14 . A method for automatic determination of registration accuracy between a first image of a first object and a second image of a second object, comprising:

identifying a first image element in the first object by scanning the first image sequentially by image unit;

identifying a second image element in the second object by scanning the second image sequentially by the image unit;

registering the first image element to the second image element in a shared background coordinate space;

determining an accuracy of the registering by relating the first image element and the second image element to the shared background coordinate space, calculating a first distance between the first image element and a nearest point in the shared background coordinate space, calculating a second distance between the second image element and the nearest point in the shared background coordinate space, and calculating a difference between the first distance and the second distance,

wherein

the first image and the second image are three-dimensional;

the image unit is a voxel;

the scanning of the first image sequentially is circling from a first perimeter of the first image inward; and

the scanning of the second image sequentially is circling from a second perimeter of the second image inward.

15 . The method of claim 14 , further comprising repeating the steps of the method for further first image elements and further second image elements.

16 . The method of claim 15 , wherein the registering of the first image element to the second image element in the shared background coordinate space comprises registering the further first image elements to the further second image elements in the shared background coordinate space, and minimizing a sum of the difference between the first distance and the second distance and further differences between further first distances and further second distances.

17 . The method of claim 14 , wherein the registering includes the process of calculating a transformation that aligns two or more image elements, objects, images, and/or coordinate spaces to each other.

18 . The method of claim 14 , wherein the shared background coordinate space is a coordinate space of the first image, the second image, a third unrelated space, or a fourth space that is a result of the registration.

19 . The method of claim 14 , wherein the first object is the same type as the type of the second object.

20 . The method of claim 14 , wherein the first image element is the same type as the type of the second image element.

21 . The method of claim 14 , wherein the first object is the same object as the second object.

22 . The method of claim 14 , wherein the first image element is the same image element as the second image element.

23 . The method of claim 14 , wherein an output of the accuracy determination is graphical or numerical.

24 . The method of claim 14 , where in the registering occurs before or after the identifying steps.

25 . The method of claim 14 , wherein:

the scanning of the first image sequentially is row by row; and

the scanning of the second image sequentially is row by row.