Image processing apparatus, image processing method, and computer-readable recording medium for extracting a dark portion area from an intraluminal image

Patent metadata

Field	Value
Publication number	US-9053533-B2
Application number	US-201113177045-A
Country	US
Kind code	B2
Filing date	Jul 6, 2011
Priority date	Jul 7, 2010
Publication date	Jun 9, 2015
Grant date	Jun 9, 2015

Abstract

An image processing apparatus includes a low-luminance area detecting unit that detects a low-luminance area based on pixel values of pixels of the intraluminal image; a peripheral feature data calculating unit that calculates peripheral feature data based on pixel values of periphery of the low-luminance area; and a dark portion area determining unit that determines whether or not the low-luminance area is the dark portion area based on the peripheral feature data.

First claim

What is claimed is:

1. A method of processing an image for extracting a dark portion area, which is an area inside of a lumen which receives little light, from an intraluminal image, the method comprising:
detecting a low-luminance area based on pixel values of pixels of the intraluminal image;
setting a periphery area that is expanded from the low-luminance area;
calculating peripheral feature data based on the pixel values of the periphery area of the low-luminance area after the periphery area of the low-luminance area is set; and
determining whether or not the low-luminance area is a dark portion area based on the peripheral feature data.

2. An image processing apparatus for extracting a dark portion area, which is an area inside of a lumen which receives little light, from an intraluminal image, the image processing apparatus comprising:
a processor; and
a memory storing computer-readable instructions that, when executed by the processor, implement:
a low-luminance area detecting unit that detects a low-luminance area based on pixel values of pixels of the intraluminal image;
a setting unit for setting a periphery area that is expanded from the low-luminance area;
a peripheral feature data calculating unit that calculates peripheral feature data based on pixel values of the periphery area of the low-luminance area after the periphery area of the low-luminance area is set by the setting unit; and
a dark portion area determining unit that determines whether or not the low-luminance area is a dark portion area based on the peripheral feature data.

3. The image processing apparatus according to claim 2 , wherein the low-luminance area detecting unit includes:
an initial area detecting unit that detects an initial area based on color feature data of the intraluminal image; and
an area correcting unit that corrects the initial area based on the color feature data of a periphery of the initial area or a shape of the initial area.

4. The image processing apparatus according to claim 2 , wherein the peripheral feature data calculating unit includes a concentration ratio calculating unit that calculates a concentration ratio of a plurality of gradients that is a value indicating a degree of a direction of the gradients on the periphery of the low-luminance area being directed to a side of the low-luminance area as the peripheral feature data.

5. The image processing apparatus according to claim 3 , wherein the area correcting unit includes:
an area expanding unit that expands the initial area by integrating an adjacent area having color feature data similar to the color feature data of the initial area with the initial area; and
a contour smoothing unit that corrects a contour of an image after being expanded by the area expanding unit to be smooth.

6. The image processing apparatus according to claim 3 , wherein the area correcting unit corrects the initial area by transforming the initial area by using an active contour model.

7. The image processing apparatus according to claim 4 , wherein the concentration ratio calculating unit includes:
an outside direction vector calculating unit that calculates an outside direction vector starting from the low-luminance area toward an outside direction;
a gradient vector calculating unit that calculates a gradient vector of an area present in the outside of the low-luminance area; and
an inner product calculating unit that calculates an inner product of the outside direction vector and the gradient vector.

8. The image processing apparatus according to claim 7 ,
wherein the outside direction vector calculating unit includes a normal-line vector calculating unit that calculates a normal-line vector with respect to a contour of the low-luminance area, and
wherein the normal-line vector is set to the outside direction vector.

9. The image processing apparatus according to claim 7 , wherein the outside direction vector calculating unit includes:
a gravitational center calculating unit that calculates a gravitational center of the low luminance area; and
a radiation vector calculating unit that calculates a radiation direction vector that is positioned from the gravitational center toward a radiation direction,
wherein the radiation direction vector is set as the outside direction vector.

10. The image processing apparatus according to claim 7 ,
wherein the gradient vector calculating unit includes a calculation range limiting unit, as the setting unit for setting a periphery area of the low-luminance area, that limits a range in which the gradient vector is calculated based on whether or not there is a steep gradient on the periphery of the low-luminance area.

11. The image processing apparatus according to claim 10 , wherein the calculation range limiting unit includes:
a profile calculating unit that acquires pixel values on an extension contour line that is set to be parallel to a contour of the low-luminance area on the periphery of the low-luminance area and calculates a periphery profile that indicates a change in the pixel value along the extension contour line; and
a minimum portion detecting unit that detects a minimum portion of the change in the pixel value.

12. The image processing apparatus according to claim 10 , wherein the calculation range limiting unit includes:
an inner product calculating unit that uses a contour pixel of the low-luminance area as a base point and calculates an inner product of vectors positioned toward other contour pixels that are present on both sides of the contour pixel located at the base point; and
an inner product determining unit that determines whether or not there is a steep gradient on the periphery of the low-luminance area based on a magnitude of the inner product.

13. The image processing apparatus according to claim 10 , wherein the calculation range limiting unit includes:
an edge strength calculating unit that calculates edge strength on the periphery of the low-luminance area; and
an edge-strength determining unit that determines whether or not there is a steep gradient on the periphery of the low-luminance area based on a magnitude of the edge strength.

14. The image processing apparatus according to claim 7 , wherein the gradient vector calculating unit includes a periphery smoothing unit that performs smoothing for the periphery of the low-luminance area based on frequency feature data on the periphery of the low-luminance area.

15. The image processing apparatus according to claim 14 , wherein the periphery smoothing unit includes:
a frequency feature data calculating unit that calculates the frequency feature data based on a dominant frequency component on the periphery of the low-luminance area; and
a high-frequency component removing unit that removes a high-frequency component from the periphery of the low-luminance area based on the frequency feature data.

16. The image processing apparatus according to claim 15 , wherein the high-frequency component removing unit performs a morphological process for the periphery of the low-luminance area by using a structure element of a size corresponding to the frequency feature data.

17. The image processing apparatus according to claim 15 , wherein the high-frequency component removing unit performs a low-pass filtering process for the periphery of the low-luminance area based on the frequency feature data.

18. The image processing apparatus according to claim 2 , wherein the peripheral feature data calculating unit includes a continuity calculating unit that calculates continu

Assignees

• Hirota Masashi
• Kanda Yamato
• Kitamura Makoto
• Matsuda Takehiro
• Kono Takashi
• Olympus Corp

Inventors

• Hirota Masashi
• Kanda Yamato
• Kitamura Makoto
• Matsuda Takehiro
• Kono Takashi

Classifications

• G06T2207/20224

  Image subtraction · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T2207/30028

  Colon; Small intestine · CPC title

• G06T2207/10068

  Endoscopic image · CPC title

• G06T2207/10024

  Color image · CPC title