Image processing method and capsule type endoscope device

• US 20070191677A1
• Filed: 04/09/2007
• Published: 08/16/2007
• Est. Priority Date: 10/29/2004
• Status: Abandoned Application

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: Hasegawa, Jun, Nishimura, Hirokazu
• Application Number:
  US11/784,751
• Publication Number:
  US 20070191677A1
• Time in Patent Office: Days
• US Class Current: 600/109
• CPC Class Codes: A61B 1/000094 extracting biological structures
• CPC Class Codes: A61B 1/000096 using artificial intelligence
• CPC Class Codes: A61B 1/00016 using wireless means
• CPC Class Codes: A61B 1/04 combined with photographic or television appliances
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: A61B 1/042 characterised by a proximal camera, e.g. a CCD camera
• CPC Class Codes: A61B 5/073 Intestinal transmitters
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00

Abstract

An image processing method is provided which can determine if an image obtained by capturing an image of a subject is an image inappropriate for observation and diagnosis or not. The image processing method of the present invention comprises calculating one or more feature value of each of a plurality of images including a plurality of color signals obtained by capturing an image of a subject and determining the image-captured state of each of the images by comparing the calculated feature value with a threshold value of the image-captured state determining good or bad of the image set in advance.

Claims

1. An image processing method comprising:

calculating one or more feature value of each of a plurality of images including a plurality of color signals obtained by capturing an image of a subject; and

determining an image-captured state of each of the images on the basis of the calculated feature value.

2. The image processing method according to claim 1, wherein in the feature value calculating, a feature value is calculated on the basis of brightness and/or tone and/or frequency component of the image.

3. The image processing method according to claim 2, wherein in the feature value calculating, a feature value is calculated on the basis of brightness and/or tone and/or frequency component for each pixel constituting the image.

4. The image processing method according to claim 2, wherein in the feature value calculating, a feature value is calculated on the basis of brightness of at least one color signal in the plurality of color signals constituting the image.

5. The image processing method according to claim 2, further comprising:

extracting tone of the image,

wherein in the feature value calculating, a feature value is calculated on the basis of the tone of the image extracted in the tone extracting.

6. The image processing method according to claim 2, further comprising:

extracting frequency component of the image, wherein

in the feature value calculating, a feature value is calculated on the basis of the frequency component of the image extracted in the frequency component extracting.

7. The image processing method according to claim 6, wherein the frequency component extracting further includes:

applying band pass filtering for extracting a frequency component constituting a living mucous surface structural component in the image; and

calculating frequency power of the extracted frequency component; and

the feature value calculating further includes

setting a calculation result by the frequency power calculation as a feature value.

8. The image processing method according to claim 1, wherein in the image-captured state determining, determination is made on an image-captured state including the image-captured state for the living mucous surface in the image and/or a target to be captured other than the living mucous surface.

9. The image processing method according to claim 8, wherein in the image-captured state determining, determination is made on a dark space and/or high light and/or defocusing due to excessive close-up, submersion under water or movement as the image-captured state for the living mucous surface.

10. The image processing method according to claim 8, wherein in the image-captured state determining, determination is made on residues and/or bubbles and/or liquid in a digestive tract as the target to be captured other than the living mucous surface.

11. The image processing method according to claim 9, wherein in the image-captured state determining, the image is classified as a dark space image in an inappropriate image-captured state on the basis of at least one of the number of pixels smaller than a predetermined value in the image and a proportion of pixels smaller than the predetermined value in the image, and a feature value on the basis of the brightness calculated in the feature value calculating.

12. The image processing method according to claim 10, wherein in the image-captured state determining, the image is classified as a dark space image in an inappropriate image-captured state on the basis of at least one of the number of pixels smaller than a predetermined value in the image and a proportion of pixels smaller than the predetermined value in the image, and a feature value on the basis of the brightness calculated in the feature value calculating.

13. The image processing method according to claim 9, wherein in the image-captured state determining, the image is classified as a high light image in an inappropriate image-captured state on the basis of at least one of the number of pixels larger than a predetermined value in the image and a proportion of pixels larger than the predetermined value in the image, and a feature value on the basis of the brightness calculated in the feature value calculating.

14. The image processing method according to claim 10, wherein in the image-captured state determining, the image is classified as a high light image in an inappropriate image-captured state on the basis of at least one of the number of pixels larger than a predetermined value in the image and a proportion of pixels larger than the predetermined value in the image, and a feature value on the basis of the brightness calculated in the feature value calculating.

15. The image processing method according to claim 9, wherein in the image-captured state determining, the image is classified as an image in the inappropriate image-captured state on the basis of at least one of the number of pixels having a predetermined tone in the image and a proportion of pixels having the predetermined tone in the image, and a feature value on the basis of the tone calculated in the feature value calculating.

16. The image processing method according to claim 10, wherein in the image-captured state determining, the image is classified as an image in the inappropriate image-captured state on the basis of at least one of the number of pixels having a predetermined tone in the image and a proportion of pixels having the predetermined tone in the image, and a feature value on the basis of the tone calculated in the feature value calculating.

17. The image processing method according to claim 9, wherein in the image-captured state determining, determination is made on whether the image is in the inappropriate image-captured state or not on the basis of a linear discriminant function using the feature value on the basis of the tone.

18. The image processing method according to claim 10, wherein in the image-captured state determining, determination is made on whether the image is in the inappropriate image-captured state or not on the basis of a linear discriminant function using the feature value on the basis of the tone.

19. The image processing method according to claim 9, wherein in the image-captured state determining, determination is made on whether the image is in the inappropriate image-captured state or not by comparing the feature value on the basis of the frequency with a predetermined threshold value.

20. The image processing method according to claim 10, wherein in the image-captured state determining, determination is made on whether the image is in the inappropriate image-captured state or not by comparing the feature value on the basis of the frequency with a predetermined threshold value.

21. A capsule type endoscope device comprising:

an image pickup device for generating a plurality of images including a plurality of color signals by capturing an image of a subject; and

an image processing device for calculating one or more feature value of each of the images and determining an image-captured state of the image on the basis of the calculated feature value for each of the images so as to control processing on the basis of the determination result.

22. The capsule type endoscope device according to claim 21, further comprising:

a memory device for storing the image; and

a display device for displaying the image, wherein

the image processing device controls processing relating to the memory device and/or display device and controls not to execute storing and/or display of the image determined as in the image-captured state including those other than the living mucous surface.

23. A capsule type endoscope device comprising:

image generating section which generates a plurality of images including a plurality of color signals by capturing an image of a subject;

feature value calculating section which calculates one or more feature value of each of the images;

image-captured state determining section which determines an image-captured state of each of the images on the basis of the calculated feature value; and

control section which controls processing on the basis of a determination result in the image-captured state determining section.

24. The capsule type endoscope device according to claim 23, further comprising:

storing section which stores the image; and

display section which displays the image, wherein

the control section controls processing relating to the storing section and/or display section of the image and controls not to store and/or display an image determined by the image-captured state determining section as in an image-captured state including those other than the living mucous surface.