IP Library › Granted Patent US 8,682,048
Granted Patent B2
US 8,682,048 · App. 13/343,796 · Granted Mar 25, 2014

Image processing device, image processing method, computer-readable recording device

Inventors: Masashi Hirota (Hachioji, JP); Yamato Kanda (Hino, JP); Makoto Kitamura (Hachioji, JP); Takeshi Kono (Tachikawa, JP)
Assignee: Olympus Corporation
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 8,682,048
App. No.
13/343,796
Granted
Mar 25, 2014
Kind
B2
Abstract

In an image processing device that discriminates between a mucosal region and a non-mucosal region that are contained in an intraluminal image, the image processing device includes a residue candidate region detecting unit that detects a residue candidate region to be discriminated whether the candidate region is a mucosal region or not, on the basis of a feature data of each pixel that constitutes the intraluminal image, a structure edge region detecting unit that detects a structure edge contained in the intraluminal image, and an approximate structure edge line calculating unit and an overlap deciding unit that discriminate whether the residue candidate region is a mucosal region or not, based on a relative positional relationship between the structure edge and the residue candidate region.

Claims (56)

1. An image processing device that discriminates between a mucosal region and a non-mucosal region that are contained in an intraluminal image, the image processing device comprising:

a processor; and

a memory storing computer readable instructions that, when executed by the processor, implement:

a candidate region detecting unit that detects a candidate region to be discriminated whether the region is a mucosal region or not, on the basis of a feature data of each pixel that constitutes the intraluminal image;

a structure edge region detecting unit that detects a structure edge contained in the intraluminal image; and

a region discriminating unit that discriminates whether the candidate region is a mucosal region or not, on the basis of a relative positional relationship between the structure edge and the candidate region;

wherein the region discriminating unit comprises:

an approximate structure edge line calculating unit that calculates an approximate structure edge line as an approximate line of the structure edge; and

an overlap deciding unit that decides whether the approximate structure edge line and the candidate region overlap; and

the region discriminating unit discriminates whether the candidate region is a mucosal region on the basis of a result of a decision by the overlap deciding unit.

2. The image processing device according to claim 1 , wherein the non-mucosal region is a residue region that overlaps the mucosal region.

3. The image processing device according to claim 1 , wherein the candidate region detecting unit detects the candidate region on the basis of color feature data of the each pixel.

4. The image processing device according to claim 1 , wherein the structure edge region detecting unit detects the structure edge by using one color component that is farthest from a light absorption zone in a lumen among a plurality of color components that constitute the intraluminal image.

5. The image processing device according to claim 1 , wherein

the structure edge region detecting unit comprises:

a first differential strength calculating unit that calculates a first differential strength of each pixel by using a first color component of the each pixel;

a second differential strength calculating unit that calculates a second differential strength of each pixel by using a second color component of the each pixel;

a normalizing unit that normalizes the second differential strength on the basis of a strength ratio between the first and second color components; and

a threshold value processing unit that discriminates that the pixel indicates a structure edge, when the first differential strength and the normalized second differential strength are both equal to or larger than a predetermined threshold value.

6. The image processing device according to claim 1 , wherein the structure edge detecting unit detects the structure edge in a peripheral region that surrounds the candidate region.

7. The image processing device according to claim 6 , wherein

the structure edge region detecting unit comprises:

a homothetic curve calculating unit that calculates a plurality of homothetic curves, each homothetic curve formed of pixels at equal distances from an outline of the candidate region and having a shape similar to the outline of the candidate region, the homothetic curves having mutually different distances from the outline of the candidate region;

an edge position detecting unit that detects edge positions of the plurality of homothetic curves; and

a continuity deciding unit that decides continuity of edge coordinates between adjacent homothetic curves among the plurality of homothetic curves.

8. The image processing device according to claim 1 , wherein the approximate structure edge line calculating unit labels a plurality of the structure edges detected near the candidate region, and calculates an approximate structure edge line for each of the labeled structure edges.

9. The image processing device according to claim 1 , wherein the approximate structure edge line calculating unit comprises a function approximating unit that function approximates the structure edge.

10. The image processing device according to claim 9 , wherein the function approximating unit calculates a vector that is orthogonal to a gradient direction of a pixel value of a pixel that is positioned on the structure edge, and performs a function approximation on the basis of the vector.

11. The image processing device according to claim 9 , wherein the function approximating unit calculates an eigenvector of a Hessian matrix on the basis of a pixel value of a pixel that is positioned on the structure edge, and performs a function approximation on the basis of the eigenvector.

12. The image processing device according to claim 9 , wherein the function approximating unit performs a function approximation on the basis of coordinates of a pixel that is positioned on the structure edge.

13. The image processing device according to claim 1 , wherein the overlap deciding unit performs a decision on the basis of an angle formed by a normal line of the outline and the approximate structure edge line, at a position where coordinates of the approximate structure edge line and coordinates of the candidate region match.

14. The image processing device according to claim 1 , wherein the region discriminating unit further comprises a similarity calculating unit that calculates a similarity between an outline of the candidate region and the approximate structure edge line, and discriminates whether the candidate region is a mucosal region, on the basis of the similarity.

15. An image processing method for discriminating between a mucosal region and a non-mucosal region that are contained in an intraluminal image, the image processing method comprising:

candidate region detecting to detect a candidate region to be discriminated whether the region is a mucosal region or not, on the basis of a feature data of each pixel in the intraluminal image;

structure edge detecting to detect a structure edge contained in the intraluminal image; and

region discriminating to discriminate whether the candidate region is a mucosal region or not, on the basis of a relative positional relationship between the structure edge and the candidate region;

wherein the region discriminating comprises:

calculating an approximate structure edge line as an approximate line of the structure edge; and

deciding whether the approximate structure edge line and the candidate region overlap; and

the region discriminating discriminates whether the candidate region is a mucosal region on the basis of a result of a decision by the overlap deciding.

16. A computer-readable recording device with an executable program stored thereon, wherein the program instructs a processor to perform:

candidate region detecting to detect a candidate region to be discriminated whether the region is a mucosal region or not, on the basis of a feature data of each pixel in the intraluminal image;

structure edge detecting to detect a structure edge contained in the intraluminal image; and

region discriminating to discriminate whether the candidate region is a mucosal region or not, on the basis of a relative positional relationship between the structure edge and the candidate region;

wherein the region discriminating comprises:

calculating an approximate structure edge line as an approximate line of the structure edge; and

deciding whether the approximate structure edge line and the candidate region overlap; and

the region discriminating discriminates whether the candidate region is a mucosal region on the basis of a result of a decision by the overlap deciding.

17. An image processing device that discriminates between a mucosal region and a non-mucosal region that are contained in an intraluminal image, the image processing device comprising:

a candidate region detecting unit that detects a candidate region to be discriminated whether the region is a mucosal region or not, on the basis of a feature data of each pixel that constitutes the intraluminal image;

a structure edge region detecting unit that detects a structure edge contained in the intraluminal image; and

a region discriminating unit that discriminates whether the candidate region is a mucosal region or not, on the basis of a relative positional relationship between the structure edge and the candidate region;

wherein the region discriminating unit comprises:

an approximate structure edge line calculating unit that calculates an approximate structure edge line as an approximate line of the structure edge; and

an overlap deciding unit that decides whether the approximate structure edge line and the candidate region overlap; and

the region discriminating unit discriminates whether the candidate region is a mucosal region on the basis of a result of a decision by the overlap deciding unit.

Assignments (2)
CHANGE OF ADDRESS Recorded Jun 27, 2016
From: OLYMPUS CORPORATION
To: OLYMPUS CORPORATION
Reel/Frame 039344/0502 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 5, 2012
From: HIROTA, MASASHI; KANDA, YAMATO; KITAMURA, MAKOTO; KONO, TAKASHI
To: OLYMPUS CORPORATION
Reel/Frame 027482/0603 →
Priority Claims (1)
JP 2011-002984 · Jan 11, 2011 · national
Continuity (1)
Related Publication 20120177259A1 · Jul 12, 2012