# US 2016/0260219 A1 · Method and apparatus for image registration in the gradient domain

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0260219 A1
- Document ID: US20160260219A1
- Status: Published application
- Kind: A1
- Application number: 14/635,027
- Filed: 2015-03-02
- Published: 2016-09-08
- Earliest claimed: 2015-03-02
- Assignees: Nokia Technologies Oy
- Applicants: Nokia Technologies OY
- Inventors: Xin Chen; Junzhou Huang
- Web page: https://patentgrep.com/patent/US20160260219A1

## CPC

- G06T 7/30: Determination of transform parameters for the alignment of images, i.e. image registration
- G06T 11/60: Creating or editing images; Combining images with text
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method, apparatus and computer program product are provided for image registration in the gradient domain. A method is provided including receiving a first image and second image; and registering the first and second images in a gradient domain. The registration of the first and second images in the gradient domain includes applying an energy minimization function based on total variation.

## Claims

### Claim 1

A method comprising:
receiving a first image and second image; and
registering the first and second images in a gradient domain, wherein registration of the first and second images in the gradient domain comprises applying an energy minimization function based on total variation.

### Claim 2 (depends on 1)

The method of claim 1, wherein registering the first and second images in the gradient domain comprises:
determining parameters for a first image registration;
registering the first and second images based on the first image registration parameters;
determining a gradient error associated with the first image registration;
determining if the gradient error satisfies a predetermined minimization value; and
generating a composite image, in an instance in which the gradient error satisfies the predetermined minimization value.

### Claim 3 (depends on 2)

The method of claim 2, wherein registering the first and second images in the gradient domain further comprises:
incrementing the image registration parameters for a second image registration;
registering the first and second image based on the second image registration parameters;
determining the gradient error associated with the second image registration;
comparing the gradient error of the first image registration to the gradient error of the second image registration;
determining if a change in gradient error between the first image registration and the second image registration satisfies a predetermined gradient change value; and
generating a composite image, in an instance in which the change in gradient error satisfies the predetermined gradient change value.

### Claim 4 (depends on 3)

The method of claim 3, wherein registering the first and second images in the gradient domain further comprises:
reperforming the incrementing the registration parameters, registering the first and second image determining the gradient error, comparing the gradient errors.

### Claim 5 (depends on 1)

The method of claim 1, wherein registration of the first and second images creates a gradient error, wherein the gradient error comprises total variation.

### Claim 6 (depends on 1)

The method of claim 1, wherein registering the first and second images in the gradient domain is based on a gradient descent algorithm.

### Claim 7 (depends on 1)

The method of claim 1, wherein a gradient in the gradient domain comprises an edge within an image.

### Claim 8

An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the processor, cause the apparatus to at least:
receive a first image and second image; and
register the first and second images in a gradient domain, wherein registration of the first and second images in the gradient domain comprises applying an energy minimization function based on total variation.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein registering the first and second images in the gradient domain comprises:
determining parameters for a first image registration;
registering the first and second images based on the first image registration parameters;
determining a gradient error associated with the first image registration;
determining if the gradient error satisfies a predetermined minimization value; and
generating a composite image, in an instance in which the gradient error satisfies the predetermined minimization value.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein registering the first and second images in the gradient domain further comprises:
incrementing the image registration parameters for a second image registration;
registering the first and second image based on the second image registration parameters;
determining the gradient error associated with the second image registration;
comparing the gradient error of the first image registration to the gradient error of the second image registration;
determining if a change in gradient error between the first image registration and the second image registration satisfies a predetermined gradient change value; and
generating a composite image, in an instance in which the change in gradient error satisfies the predetermined gradient change value.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein registering the first and second images in the gradient domain further comprises:
reperforming the incrementing the registration parameters, registering the first and second image determining the gradient error, comparing the gradient errors.

### Claim 12 (depends on 8)

The apparatus of claim 8, wherein registration of the first and second images creates a gradient error, wherein the gradient error comprises total variation.

### Claim 13 (depends on 8)

The apparatus of claim 8, wherein registering the first and second images in the gradient domain is based on a gradient descent algorithm.

### Claim 14 (depends on 8)

The apparatus of claim 8, wherein a gradient in the gradient domain comprises an edge within an image.

### Claim 15

A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions configured to:
receive a first image and second image; and
register the first and second images in a gradient domain, wherein registration of the first and second images in the gradient domain comprises applying an energy minimization function based on total variation.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein registering the first and second images in the gradient domain comprises:
determining parameters for a first image registration;
registering the first and second images based on the first image registration parameters;
determining a gradient error associated with the first image registration;
determining if the gradient error satisfies a predetermined minimization value; and
generating a composite image, in an instance in which the gradient error satisfies the predetermined minimization value.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein registering the first and second images in the gradient domain further comprises:
incrementing the image registration parameters for a second image registration;
registering the first and second image based on the second image registration parameters;
determining the gradient error associated with the second image registration;
comparing the gradient error of the first image registration to the gradient error of the second image registration;
determining if a change in gradient error between the first image registration and the second image registration satisfies a predetermined gradient change value; and
generating a composite image, in an instance in which the change in gradient error satisfies the predetermined gradient change value.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein registering the first and second images in the gradient domain further comprises:
reperforming the incrementing the registration parameters, registering the first and second image determining the gradient error, comparing the gradient errors.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein registration of the first and second images creates a gradient error, wherein the gradient error comprises total variation.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein registering the first and second images in the gradient domain is based on a gradient descent algorithm.

### Claim at position 21

21-28. (canceled)
