IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND IMAGE PROCESSING PROGRAM PRODUCT

• US 20090148014A1
• Filed: 11/25/2008
• Published: 06/11/2009
• Est. Priority Date: 05/26/2006
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: KANDA, Yamato
• Granted Patent: US 8,116,531 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

An image processing apparatus includes an edge intensity calculator which calculates an edge intensity of a pixel in an image; and a correlation value calculator which calculates a correlation value between the calculated edge intensity and a bubble model set in advance based on characteristics of a bubble image. The apparatus also includes a bubble area detector which detects a bubble area based on the calculated correlation value.

Claims

1. An image processing apparatus, comprising:

an edge intensity calculator which calculates an edge intensity of a pixel in an image;

a correlation value calculator which calculates a correlation value between the calculated edge intensity and a bubble model set in advance based on characteristics of a bubble image; and

a bubble area detector which detects a bubble area based on the calculated correlation value.

2. The image processing apparatus according to claim 1, wherein

the correlation value calculator calculates correlation values with plural kinds of bubble models, and

the bubble area detector detects the bubble area based on the correlation values calculated with the plural kinds of bubble models.

3. The image processing apparatus according to claim 1, further comprising an area divider which divides the image into areas based on an edge in the image, wherein

the bubble area detector detects the bubble area based on the correlation value and a result of the area division.

4. The image processing apparatus according to claim 1, wherein the bubble model is a template pattern having a high intensity structural part of an arc shape.

5. The image processing apparatus according to claim 1, wherein the bubble model is a template pattern having a high intensity structural part of a ring shape.

6. The image processing apparatus according to claim 1, wherein the bubble model is a template pattern having a high intensity structural part of a ring shape and another high intensity structural part positioned inside the ring shape.

7. The image processing apparatus according to claim 1, wherein the edge intensity calculator uses a processing of a quadratic differentiation for each direction to calculate the edge intensity.

8. The image processing apparatus according to claim 1, further comprising a morphologic processor which performs a morphologic processing with respect to a detection result of the bubble area detector.

9. The image processing apparatus according to claim 1, wherein the image is an image captured in a body cavity.

10. An image processing program product having a computer readable medium including programmed instructions for detecting a bubble area in an image, wherein the instructions, when executed by an image processing apparatus, cause the image processing apparatus to perform:

calculating an edge intensity of a pixel in an image;

calculating a correlation value between the calculated edge intensity and a bubble model set in advance based on characteristics of a bubble image; and

detecting a bubble area based on the calculated correlation value.

11. The image processing program product according to claim 10, wherein

correlation values are calculated with plural kinds of bubble models in the calculating, and

the bubble area is detected based on the correlation values calculated with the plural kinds of bubble models in the detecting.

12. The image processing program product according to claim 10, wherein the instructions further cause the image processing apparatus to execute dividing the image into areas based on an edge in the image, and wherein

the bubble area is detected based on the correlation value and a result of the area division in the detecting.

13. The image processing program product according to claim 10, wherein the bubble model used for calculating the correlation value is a template pattern having a high intensity structural part of an arc shape.

14. The image processing program product according to claim 10, wherein the bubble model used for calculating the correlation value is a template pattern having a high intensity structural part of a ring shape.

15. The image processing program product according to claim 10, wherein the bubble model used for calculating the correlation value is a template pattern having a high intensity structural part of a ring shape and another high intensity structural part positioned inside the ring shape.

16. The image processing program product according to claim 10, wherein a processing of a quadratic differentiation for each direction is used to calculate the edge intensity in the calculating.

17. The image processing program product according to claim 10, wherein the instructions further cause the image processing apparatus to execute performing a morphologic processing with respect to a detection result of the bubble area detecting.

18. The image processing program product according to claim 10, wherein the image is an image captured in a body cavity.

19. An image processing method, comprising:

calculating an edge intensity of a pixel in an image;

calculating a correlation value between the calculated edge intensity and a bubble model set in advance based on characteristics of a bubble image; and

detecting a bubble area based on the calculated correlation value.