Image processing apparatus, image processing program recording medium, and image processing method

• US 8,396,271 B2
• Filed: 12/03/2010
• Issued: 03/12/2013
• Est. Priority Date: 06/05/2008
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: Kanda, Yamato
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US12/959,469
• Publication Number:
  US 20110069876A1
• Time in Patent Office: 830 Days
• Field of Search: 382/100, 382/107, 382/108, 382128-134, 382/155, 382/168, 382/173, 382/181, 382/184, 382/190, 382/199, 382/209, 382/219, 382/232, 382/254, 382/274, 382/276, 382/286, 382/294, 382/305, 382/312, 382/321, 600/476, 600/178
• US Class Current: 382/128
• CPC Class Codes: A61B 1/00052 positioned at proximal end of the endoscope body
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• 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 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/215 Motion-based segmentation

Abstract

An image processing apparatus includes: a category area dividing unit that divides each image constituting the time-series images of an object to be examined, which are captured in time series, into category areas including an examined area and an abnormal candidate area, the examined area showing the object to be examined, the abnormal candidate area being possibly an abnormal area showing an abnormal site of the object to be examined; an optical flow calculator that calculates optical flows of the examined area and the abnormal candidate area from images constituting the time-series images; and an abnormal area detector that compares the optical flow of the examined area and the optical flow of the abnormal candidate area, and detects the abnormal candidate area as the abnormal area according to the result of the comparison.

Claims

1. An image processing apparatus comprising:

a category area dividing unit that divides each image constituting time-series images of an object to be examined, which are captured in time series, into category areas including an examined area and an abnormal candidate area, the examined area showing the object to be examined, the abnormal candidate area being possibly an abnormal area showing an abnormal site of the object to be examined;

an optical flow calculator that calculates optical flows of the examined area and the abnormal candidate area from images constituting the time-series images; and

an abnormal area detector that compares the optical flow of the examined area and the optical flow of the abnormal candidate area, and detects the abnormal candidate area as the abnormal area according to the result of the comparison.

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

the category area dividing unit includes

an image dividing unit that divides the image into a plurality of divided areas;

a feature data calculator that calculates feature data of each of the divided areas; and

an area classifying unit that classifies the divided areas into predetermined categories according to the feature data, and

the category area dividing unit divides the image into the category areas according to the result of the classification of the divided areas by the area classifying unit.

3. The image processing apparatus according to claim 2, wherein the image dividing unit includes an edge extracting unit that extracts an edge of the image and divides the image into the plurality of divided areas according to the edge.

4. The image processing apparatus according to claim 3, wherein the edge extracting unit extracts an edge of the color component corresponding to the absorption wavelength band of blood.

5. The image processing apparatus according to claim 1, wherein the optical flow calculator calculates, as the optical flow of the examined area, an optical flow of an examined area positioned proximate to the abnormal candidate area.

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

the optical flow calculator includes

a structure area extracting unit that extracts a structure area from the image constituting the time-series images;

and

a corresponding area extracting unit that extracts a corresponding area, which corresponds to the structure area, from an image that is captured at a time different from a time at which the image from which the structure area is extracted is captured, and

the optical flow calculator calculates the optical flows according to position information of the structure area and the corresponding area.

7. The image processing apparatus according to claim 1, wherein the abnormal area detector detects the abnormal candidate area as the abnormal area when the optical flow of the abnormal candidate area is similar to the optical flow of the examined area.

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

the abnormal area detector includes

an abnormal candidate optical flow feature data calculator that calculates feature data of the optical flow of the abnormal candidate area;

and

an examined optical flow feature data calculator that calculates feature data of the optical flow of the examined area positioned proximate to the abnormal candidate area, and

the abnormal area detector detects the abnormal candidate area as the abnormal area when a difference between the feature data of the optical flow of the abnormal candidate area and the feature data of the optical flow of the examined area is equal to or less than a predetermined value.

9. The image processing apparatus according to claim 8, wherein the feature data of the optical flows is calculated at least according to directions or magnitudes of the optical flows.

10. The image processing apparatus according to claim 1, wherein the time-series images are in-vivo images of a lumen.

11. The image processing apparatus according to claim 10, wherein the optical flow calculator calculates the optical flows using a color component corresponding to an absorption wavelength band of blood.

12. The image processing apparatus according to claim 1, wherein the examined area is a mucosa area.

13. An image processing program recording medium having stored thereon instructions that causes an image processing apparatus to perform:

a category area dividing procedure that divides each image constituting time-series images of an object to be examined, which are captured in time series, into category areas including an examined area and an abnormal candidate area, the examined area showing the object to be examined, the abnormal candidate area being possibly an abnormal area showing an abnormal site of the object to be examined;

an optical flow calculating procedure that calculates optical flows of the examined area and the abnormal candidate area from images constituting the time-series images; and

an abnormal area detecting procedure that compares the optical flow of the examined area and the optical flow of the abnormal candidate area, and detects the abnormal candidate area as the abnormal area according to the result of the comparison.

14. An image processing method comprising:

a category area dividing step that divides each image constituting time-series images of an object to be examined, which are captured in time series, into category areas including an examined area and an abnormal candidate area, the examined area showing the object to be examined, the abnormal candidate area being possibly an abnormal area showing an abnormal site of the object to be examined;

an optical flow calculating step that calculates optical flows of the examined area and the abnormal candidate area from images constituting the time-series images; and

an abnormal area detecting step that compares the optical flow of the examined area and the optical flow of the abnormal candidate area, and detects the abnormal candidate area as the abnormal area according to the result of the comparison.