Image processing device, endoscope apparatus, isolated point noise correction method, and information storage device

Patent metadata

Field	Value
Publication number	US-9367902-B2
Application number	US-201414541682-A
Country	US
Kind code	B2
Filing date	Nov 14, 2014
Priority date	Jun 19, 2012
Publication date	Jun 14, 2016
Grant date	Jun 14, 2016

Abstract

An image processing device includes an isolated point noise detection section, and an isolated point noise correction section. The isolated point noise detection section determines whether or not isolated point noise is included within a given area based on a first index value that represents the range of first to nth pixel values being obtained by arranging the pixel values of pixels within the given area including an attention pixel in ascending or descending order, and a second index value that represents the range of a pixel value group being obtained by excluding at least one of the first pixel value and the nth pixel value from the first to nth pixel values. The isolated point noise detection section determines whether or not the attention pixel is a pixel that corresponds to isolated point noise when it has been determined that isolated point noise is included within the given area.

First claim

What is claimed is:

1. An image processing device comprising:
a hardware processor which is configured to perform:
an isolated point noise detection process that detects an isolated point noise that is included in an image; and
an isolated point noise correction process that corrects the isolated point noise detected by the isolated point noise detection process,

wherein the isolated point noise detection process includes an isolated point noise presence/absence determination process and an attention pixel isolated point noise determination process,
wherein the isolated point noise presence/absence determination process determines whether or not the isolated point noise is included within a given area based on a first index value that represents a range of first to nth pixel values, and a second index value that represents a range of a pixel value group, the given area including an attention pixel that is an isolated point noise detection target, the first to nth pixel values being obtained by arranging pixel values of pixels within the given area in ascending or descending order, and the pixel value group being obtained by excluding at least one of the first pixel value and the nth pixel value from the first to nth pixel values, and
wherein the attention pixel isolated point noise determination process determines whether or not the attention pixel is a pixel that corresponds to the isolated point noise when it has been determined that the isolated point noise is included within the given area.

2. The image processing device as defined in claim 1 , wherein the isolated point noise presence/absence determination process calculates a difference between the first pixel value and the nth pixel value as the first index value, and calculates a difference between a largest value and a smallest value among pixel values included in the pixel value group as the second index value.

3. The image processing device as defined in claim 2 , wherein the pixel value group includes second to (n−1)th pixel values among the first to nth pixel values, and
wherein the isolated point noise presence/absence determination process calculates a difference between the second pixel value and the (n−1)th pixel value included in the pixel value group as the second index value.

4. The image processing device as defined in claim 1 , wherein the isolated point noise presence/absence determination process determines that the isolated point noise is included within the given area when the first index value is larger than a value obtained by multiplying the second index value by a first coefficient.

5. The image processing device as defined in claim 1 , wherein the attention pixel isolated point noise determination process determines that the attention pixel is the pixel that corresponds to the isolated point noise when an absolute difference value between a given value within the range of the pixel value group and a pixel value of the attention pixel is larger than a value obtained by multiplying the second index value by a second coefficient.

6. The image processing device as defined in claim 5 , wherein the given value is a median value among pixel values included in the pixel value group.

7. The image processing device as defined in claim 1 , wherein the isolated point noise correction process corrects the attention pixel using a value obtained from the first to nth pixel values when it has been determined that the attention pixel is a pixel that corresponds to the isolated point noise.

8. The image processing device as defined in claim 7 , wherein the isolated point noise correction process corrects the attention pixel by replacing a pixel value of the attention pixel with a median value among the first to nth pixel values.

9. The image processing device as defined in claim 1 , wherein the image for which the isolated point noise is corrected is an image in which pixels that differ in color are disposed, and wherein the first to nth pixel values are pixel values of pixels among pixels included in the given area that are identical in color with the attention pixel.

10. The image processing device as defined in claim 1 , wherein the hardware processor is further configured to perform a highlight correction processing process that determines whether or not the attention pixel that has been corrected by the isolated point noise correction process is a pixel within a highlight area, and that returns a pixel value of the attention pixel to a pixel value before the attention pixel is corrected by the isolated point noise correction process when it has been determined that the attention pixel is a pixel within the highlight area.

11. The image processing device as defined in claim 10 , wherein the image for which the isolated point noise is corrected is an image in which pixels that differ in color are disposed, and
wherein the highlight correction processing process includes an attention pixel highlight determination process that compares the pixel value of the attention pixel that has not been corrected by the isolated point noise correction process with pixel values of different-color adjacent pixels that differ in color from the attention pixel and are situated adjacent to the attention pixel to determine whether or not the attention pixel is a candidate for a pixel within the highlight area.

12. The image processing device as defined in claim 11 , wherein the attention pixel highlight determination process compares a pixel value of a pixel among the different-color adjacent pixels that has not been corrected by the isolated point noise correction process with the pixel value of the attention pixel that has not been corrected by the isolated point noise correction process.

13. The image processing device as defined in claim 11 , wherein the hardware processor is further configured to perform a white balance correction process on the different-color adjacent pixels, and
wherein the attention pixel highlight determination process determines whether or not the attention pixel is a candidate for a pixel within the highlight area based on the different-color adjacent pixels that have been subjected to the white balance correction process.

14. The image processing device as defined in claim 11 , wherein the attention pixel highlight determination process selects a pixel among the different-color adjacent pixels that has a pixel value closest to the pixel value of the attention pixel as a selected pixel, and
wherein the highlight correction processing process includes an adjacent pixel highlight determination process that compares the pixel value of the selected pixel with pixel values of pixels that are identical in color with the selected pixel and are situated at a given position with respect to the selected pixel to determine whether or not the selected pixel is a pixel within the highlight area, when the attention pixel highlight determination process has determined that the attention pixel is a candidate for a pixel within the highlight area.

15. The image processing device as defined in claim 14 , wherein the highlight correction processing process includes an attention pixel highlight decision process that determines that the attention pixel is a pixel within the highlight area when the attention pixel highlight determination process has determined that the attention pixel is the candidate for the pixel within the highlight area, and the adjacent pixel highlight determination process has determined that the different-color adjacent pixels are pixels within the highlight area.

16. An endoscope apparatus comprising the image processing de

Assignees

• Olympus Corp
• Olympus Coporation

Inventors

• Sasaki Hiroshi

Classifications

• H04N25/683

  by defect estimation performed on the scene signal, e.g. real time or on the fly detection · CPC title

• G06T2207/10068

  Endoscopic image · CPC title

• G06T5/002 Primary

  Physics · mapped topic

• G06T2207/10024

  Color image · CPC title

• H04N5/3675

  Electricity · mapped topic