# US 6,731,806 B1 · Region growing based noise reduction method for digital images

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

- Number: US 6,731,806 B1
- Document ID: US6731806B1
- Status: Granted
- Kind: B1
- Application number: 09/415,365
- Filed: 1999-10-08
- Granted: 2004-05-04
- Earliest claimed: 1999-10-08
- Assignees: Eastman Kodak Company
- Inventors: Edward B. Gindele
- Web page: https://patentgrep.com/patent/US6731806B1

## CPC

- G06T 5/20: using local operators
- G06V 10/30: Noise filtering
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for removing noise from a pixel of a digital image channel includes the steps of: storing an original value of the pixel of interest and using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels. The method further includes using the neighborhood region of cleaning pixels and the value of the pixel of interest to replace the original value of the pixel of interest with a noise cleaned pixel value.

## Claims

### Claim 1

A method for removing noise from a pixel of a digital image channel comprising the steps of:
(a) storing an original value of the pixel of interest;
(b) using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels; wherein the neighborhood region of cleaning pixels is chosen from one or more predetermined pixel processing paths contiguous with the pixel of interest; and the length of the predetermined pixel processing paths is based on the difference of the value of the pixel of interest and the values of the pixels contained in the pixel processing paths; and
(c) using the neighborhood region of cleaning pixels and the value of the pixel of interest to replace the original value of the pixel of interest with a noise cleaned pixel value.

### Claim 2 (depends on 1)

The method of claim 1 wherein step (c) further comprises calculating a noise cleaned pixel value based on the difference between the value of the pixel of interest and the values of the pixels contained in the neighborhood of cleaning pixels.

### Claim 3 (depends on 1)

The method of claim 1 wherein step (c) further comprises calculating a noise cleaned pixel value based on the statistical mean of the values of the pixels contained in the neighborhood of cleaning pixels.

### Claim 4

A method for removing noise on a pixel by pixel basis from pixels of a digital image channel comprising the steps of:
(a) storing an original value of the pixel of interest;
(b) using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels;
(c) using the neighborhood region of cleaning pixels and the value of the pixel of interest to change the original value of the pixel of interest so that it has been noise cleaned; and calculating a noise cleaned pixel value based on the difference between the value of the pixel of interest and the values of the pixels contained in the neighborhood of cleaning pixels; and
(d) repeating steps (a)-(c) for other pixels of interest.

### Claim 5

A method for removing noise from a pixel of a digital image channel comprising the steps of:
(a) storing an original value of the pixel of interest;
(b) using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels; wherein the neighborhood region of cleaning pixels is chosen from one or more predetermined pixel processing paths contiguous with the pixel of interest that are disposed along radial directions in relation to the pixel of interest; and the length of the pixel processing paths is based on the difference of the value of the pixel of interest and the values of the pixels contained in the predetermined pixel processing paths; and
(c) using the neighborhood region of cleaning pixels and the value of the pixel of interest to replace the original value of the pixel of interest with a noise cleaned pixel value.

### Claim 6 (depends on 5)

The method of claim 5 wherein step (c) further comprises calculating a noise cleaned pixel value based on the difference between the value of the pixel of interest and the values of the pixels contained in the neighborhood of cleaning pixels.

### Claim 7 (depends on 5)

The method of claim 5 wherein step (c) further comprises calculating a noise cleaned pixel value based on the statistical mean of the values of the pixels contained in the neighborhood of cleaning pixels.

### Claim 8

A method for removing noise from a pixel of a digital image channel comprising the steps of:
(a) storing an original value of the pixel of interest;
(b) using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels; and
(c) using the neighborhood region of cleaning pixels and the value of the pixel of interest to replace the original value of the pixel of interest with a noise cleaned pixel value and calculating a noise cleaned pixel value based on the difference between the value of the pixel of interest and the values of the pixels contained in the neighborhood of cleaning pixels.

### Claim 9

A method for removing noise from a pixel of a digital image channel comprising the steps of:
(a) storing an original value of the pixel of interest;
(b) using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels; wherein the neighborhood region of cleaning pixels is chosen from one or more predetermined pixel processing paths contiguous with the pixel of interest; and
(c) using the neighborhood region of cleaning pixels and the value of the pixel of interest to replace the original value of the pixel of interest with a noise cleaned pixel value based on the difference between the value of the pixel of interest and the values of the pixels contained in the neighborhood of cleaning pixels.

### Claim 10

A method for removing noise from a pixel of a digital image channel comprising the steps of:
(a) storing an original value of the pixel of interest;
(b) using the value of the pixel of interest and neighboring contiguous pixels to determine a variable shape neighborhood region of cleaning pixels; wherein the neighborhood region of cleaning pixels is chosen from one or more predetermined pixel processing paths contiguous with the pixel of interest that are contiguous with the pixel of interest and disposed along radial directions in relation to the pixel of interest; and
(c) using the neighborhood region of cleaning pixels and the value of the pixel of interest to replace the original value of the pixel of interest with a noise cleaned pixel value based on the difference between the value of the pixel of interest and the values of the pixels contained in the neighborhood of cleaning pixels.
