Image processing apparatus and image processing method

• US 8,135,192 B2
• Filed: 04/02/2009
• Issued: 03/13/2012
• Est. Priority Date: 10/02/2006
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: Matsuzaki, Hiroshi, Kanda, Yamato
• Primary Examiner(s): Taningco, Alexander H
• Application Number:
  US12/417,035
• Publication Number:
  US 20090252390A1
• Time in Patent Office: 1,076 Days
• Field of Search: 378/4, 378/5, 378/8, 378/98.11, 378/98.12, 382/128, 382/130, 382/131
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: H04N 19/142 Detection of scene cut or scene change

Abstract

An image processing apparatus for extracting images from a continuous image sequence includes a storage unit that stores image information about images constituting the image sequence; an image reading unit that reads the image information from the storage unit; and an image change amount calculating unit that calculates a predetermined image change amount between at least two images using the image information read by the image reading unit. The apparatus also includes an image change amount information adding unit that adds information about the image change amount calculated by the image change amount calculating unit to a corresponding image; and an image extracting unit that extracts a preset number of images from the image sequence based on the information added to each image by the image change amount information adding unit.

Claims

1. An image processing apparatus for extracting images from a continuous image sequence, the image processing apparatus comprising:

a storage unit that stores image information about images constituting the image sequence;

an image reading unit that reads the image information from the storage unit;

an image change amount calculating unit that calculates a predetermined image change amount between at least two images using the image information read by the image reading unit;

an image change amount information adding unit that adds information about the image change amount calculated by the image change amount calculating unit to a corresponding image; and

an image extracting unit that extracts a preset number of images from the image sequence based on the information added to each image by the image change amount information adding unit, wherein the image extracting unit rearranges the images based on the information added to each image by the image change amount information adding unit, and extracts images from the image sequence, using a result of the rearranging.

2. The image processing apparatus according to claim 1, wherein the image extracting unit rearranges the images extracted from the image sequence in a chronological order in which the images are taken.

3. The image processing apparatus according to claim 1, further comprising

a feature value calculating unit that calculates a feature value of each image contained in the image information read by the image reading unit, wherein

the image change amount calculating unit calculates, as an image change amount, a change in the feature value between at least two images, using the feature value of each image calculated by the feature value calculating unit.

4. The image processing apparatus according to claim 3, wherein

the feature value calculating unit calculates a plurality of different types of feature values of each image,

the image change amount calculating unit calculates, after calculating a change in each feature value, an integrated change amount obtained by combining results of the calculating, and

the image change amount information adding unit adds, as information about the changes in the feature values, information obtained using the integrated change amount to each image.

5. The image processing apparatus according to claim 4, wherein

the feature value calculating unit performs a normalization process on the feature values, and generates a feature vector composed of values obtained by the normalization process, and

the image change amount calculating unit calculates, as the integrated change amount, a change in the feature vector between predetermined images.

6. The image processing apparatus according to claim 3, wherein

the feature value calculating unit calculates a plurality of different types of feature values of each image, and

the image extracting unit extracts, after extracting a preset number of images from the image sequence based on the information added to each image, images based on a level of importance added to each of the feature values.

7. The image processing apparatus according to claim 3, wherein

any one of the feature values indicates the number of pixels of an image binarized with a predetermined threshold after an edge of the image is extracted.

8. The image processing apparatus according to claim 1, further comprising

a feature value calculating unit that calculates a feature value of an image contained in the image information read by the image reading unit, wherein

the image extracting unit extracts a preset number of images based on the feature value of each image calculated by the feature value calculating unit and the information added to each image by the image change amount information adding unit.

9. The image processing apparatus according to claim 8, wherein

the image feature value calculating unit calculates at least a statistical amount of pixel values of each image as the feature value, and

the image extracting unit extracts the preset number of images based on the information added to each image by the image change amount information adding unit, while excluding an image about which it is determined that the image is inappropriate as an image to be extracted based on the statistical amount of pixel values of each image calculated by the feature value calculating unit.

10. The image processing apparatus according to claim 9, wherein the image extracting unit extracts the preset number of images, while excluding an image about which it is determined that a statistical amount of pixel values of the image calculated by the feature value calculating unit is larger than a predetermined threshold and the image is too bright as an image to be extracted.

11. The image processing apparatus according to claim 9, wherein the image extracting unit extracts the preset number of images, while excluding an image about which it is determined that a statistical amount of pixel values of each image calculated by the feature value calculating unit is smaller than a predetermined threshold and the image is too dark as an image to be extracted.

12. The image processing apparatus according to claim 1, wherein the image change amount calculating unit calculates, as the image change amount, a correlation, a difference, or similarity between at least two images.

13. The image processing apparatus according to claim 1, wherein the image change amount calculating unit calculates the image change amount using a predetermined number of images at preset time intervals.

14. The image processing apparatus according to claim 1, wherein the image sequence is a sequence of in-vivo images taken by a capsule endoscope that is introduced into body cavities of a subject.

15. The image processing apparatus according to claim 1, further comprising an extraction number setting unit that sets the number of images to be extracted by the image extracting unit.

16. An image processing apparatus for extracting images from a continuous image sequence, the image processing apparatus comprising:

a storage unit that stores image information about images constituting the image sequence;

an image reading unit that reads the image information from the storage unit;

an image change amount calculating unit that calculates a predetermined image change amount between at least two images using the image information read by the image reading unit;

an image change amount information adding unit that adds information about the image change amount calculated by the image change amount calculating unit to a corresponding image;

a feature value calculating unit that calculates at least a statistical amount of pixel values as a feature value of each image contained in the image information read by the image reading unit; and

an image extracting unit that extracts an image from the image sequence based on the feature value of each image calculated by the feature value calculating unit and the information added to each image by the image change amount information adding unit, wherein

the image extracting unit extracts an image based on the information added to each image by the image change amount information adding unit, while excluding an image about which it is determined that the image is inappropriate as an image to be extracted based on the statistical amount of pixel values of each image calculated by the feature value calculating unit.

17. The image processing apparatus according to claim 16, wherein

the image extracting unit extracts images, while excluding an image about which it is determined that a statistical amount of pixel values of each image calculated by the feature value calculating unit is larger than a predetermined threshold and the image is too bright as an image to be extracted.

18. The image processing apparatus according to claim 16, wherein the image extracting unit extracts images, while excluding an image about which it is determined that a statistical amount of pixel values of each image calculated by the feature value calculating unit is smaller than a predetermined threshold and the image is too dark as an image to be extracted.

19. The image processing apparatus according to claim 16, wherein the image change amount calculating unit calculates, as the image change amount, a correlation, a difference, or similarity between at least two images.

20. The image processing apparatus according to claim 16, wherein the image change amount calculating unit calculates the image change amount using a predetermined number of images at preset time intervals.

21. The image processing apparatus according to claim 16, wherein the image sequence is a sequence of in-vivo images taken by a capsule endoscope that is introduced into body cavities of a subject.

22. The image processing apparatus according to claim 16, further comprising an extraction number setting unit that sets the number of images to be extracted by the image extracting unit.

23. An image processing method performed by a computer that enables extracting images from a continuous image sequence and includes a storage unit which stores image information about images constituting the image sequence, the image processing method comprising:

reading the image information from the storage unit;

calculating a predetermined image change amount between at least two images using the read image information;

adding information about the calculated image change amount to a corresponding image;

extracting a preset number of images from the image sequence based on the information added to each image; and

rearranging the images based on the information added to each image by the adding information step, and extracting images from the image sequence, using a result of the rearranging.

24. A computer readable storage device having a computer program product including programmed instructions, wherein the instructions, when executed by a computer that enables extracting images from a continuous image sequence and includes a storage unit which stores image information about images constituting the image sequence, cause the computer to perform:

reading the image information from the storage unit;

calculating a predetermined image change amount between at least two images using the read image information;

adding information about the calculated image change amount to a corresponding image;

extracting a preset number of images from the image sequence based on the information added to each image; and

rearranging the images based on the information added to each image by the adding information step, and extracting images from the image sequence, using a result of the rearranging.