IMAGE RECOGNITION DEVICE, FOCUS ADJUSTMENT DEVICE, IMAGING APPARATUS, IMAGE RECOGNITION METHOD AND FOCUS ADJUSTMENT METHOD

• US 20090010549A1
• Filed: 06/18/2008
• Published: 01/08/2009
• Est. Priority Date: 07/04/2007
• Status: Active Grant

• Current Assignee: Nikon Corporation
• Original Assignee: Nikon Corporation
• Inventors: MURAMATSU, Keiko
• Granted Patent: US 8,401,228 B2
• Time in Patent Office: Days
• US Class Current: 382/209
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/24323 Tree-organised classifiers
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/675 comprising setting of focusing regions
• CPC Class Codes: H04N 25/134 based on three different wavelength filter elements

Abstract

An image recognition device includes a detection unit which is configured to detect a first difference between at least a part of the first image information and the reference information, a second difference between at least a part of the second image information and the reference information, and a third difference between at least a part of the third image information and the reference information. A recognition unit is configured to make a first determination whether the first difference is within a predetermined range, and to make a second determination whether the second difference is within the predetermined range. A changing unit is configured to change the predetermined range based on the first and second determinations. The recognition unit is configured to recognize an area corresponding to the reference image in the third image information based on the third difference and the predetermined range which has been changed.

Claims

1. An image recognition device comprising:

an imaging unit configured to acquire first image information, second image information, and third image information;

a holding unit configured to hold reference information that functions as a reference image;

a detection unit connected to the holding unit and configured to detect a first difference between at least a part of the first image information and the reference information, detect a second difference between at least a part of the second image information and the reference information, and detect a third difference between at least a part of the third image information and the reference information;

a recognition unit connected to the detection unit, configured to make a first determination whether or not the first difference is within a predetermined range, and configured to make a second determination whether or not the second difference is within the predetermined range;

a changing unit connected to the recognition unit and configured to change the predetermined range based on the first determination and the second determination; and

the recognition unit being configured to recognize an area corresponding to the reference image in the third image information based on the third difference and the predetermined range which has been changed.

2. The image recognition device according to claim 1, wherein the changing unit is configured to change the predetermined range when the first determination and the second determination are same.

3. The image recognition device according to claim 1, wherein the recognition unit is configured to recognize an area corresponding to the reference image in the third image information based on whether or not the third difference is within the predetermined range which has been changed.

4. The image recognition device according to claim 1, wherein the detection unit is configured to detect plural differences between the reference information and plural parts of the third image information and determine smallest difference among the plural differences as the third difference.

5. The image recognition device according to claim 1, wherein the recognition unit is configured to recognize that an area of the image information in which the first difference is detected corresponds to the reference image when the first difference is within the predetermined range.

6. The image recognition device according to claim 1, wherein the changing unit is configured to change the predetermined range based on the first determination and the second determination, and also based on the first difference and the second difference.

7. The image recognition device according to claim 6, wherein the changing unit is configured to change the predetermined range based on an average of the first difference and the second difference.

8. The image recognition device according to claim 1, further comprising:

an update unit connected to the detection unit and configured to update the reference information based on image information based on which the first difference is detected when the first difference is determined to be within the predetermined range.

9. The image recognition device according to claim 1, wherein the changing unit is configured to expand the predetermined range when the first determination and the second determination are continuously outside the predetermined range.

10. The image recognition device according to claim 1, wherein the changing unit is configured to narrow the predetermined range when the first determination and the second determination are continuously within the predetermined range.

11. The image recognition device according to claim 1, wherein the changing unit is configured to set the predetermined range using the first difference between the at least a part of the first image information and the reference information.

12. The image recognition device according to claim 11, wherein the changing unit is configured to compare the first difference and an average value of the first difference and the second difference and configured to set the predetermined range based on the comparison.

13. A focus adjustment device in the image recognition device according to claim 1, wherein the imaging unit is configured to acquire the first image information, the second image information, and the third image information through an optical system, the focus adjustment device comprising:

a focus detection unit configured to detect a focus state of the optical system at a plurality of detection areas provided in a screen of the optical system;

a selection unit connected to the focus detection unit and configured to select at least one of the plurality of detection areas based on a recognition performed by the recognition unit and a detection performed by the focus detection unit; and

a focus adjustment unit configured to perform focus adjustment of the optical system based on the focus state detected by the focus detection unit with respect to the at least one of the plurality of detection areas selected by the selection unit.

14. The focus adjustment device according to claim 13, wherein the selection unit is configured to select one detection area based on the focus state from the plurality of detection areas contained in the area corresponding to the reference image in the third image information recognized by the recognition unit.

15. An imaging apparatus comprising the focus adjustment device according to claim 14.

16. An image recognition method comprising:

acquiring first image information, second image information, and third image information;

holding reference information that functions as a reference image;

detecting a first difference between at least a part of the first image information and the reference information;

making a first determination whether or not the first difference is within a predetermined range;

detecting a second difference between at least a part of the second image information and the reference information;

making a second determination whether or not the second difference is within the predetermined range;

changing the predetermined range based on the first determination and the second determination;

detecting a third difference between at least a part of the third image information and the reference information; and

recognizing an area corresponding to the reference image in the third image information based on the third difference and the predetermined range which has been changed.

17. The image recognition method according to claim 16, wherein the predetermined range is changed when the first determination and the second determination are same.

18. The image recognition method according to claim 16, wherein an area corresponding to the reference image in the third image information is recognized based on whether or not the third difference is within the predetermined range which has been changed.

19. The image recognition method according to claim 16, wherein plural differences between the reference information and plural parts of the third image information are detected and smallest difference among the plural differences is determined as the third difference.

20. The image recognition method according to claim 16, wherein an area of the image information in which the first difference is detected is recognized as corresponding to the reference image when the first difference is within the predetermined range.

21. The image recognition method according to claim 16, wherein the predetermined range is changed based on the first determination and the second determination, and also based on the first difference and the second difference.

22. The image recognition method according to claim 21, wherein the predetermined range is changed based on an average of the first difference and the second difference.

23. The image recognition method according to claim 16, wherein, when the first difference is determined to be within the predetermined range, the reference information is updated based on at least a part of the first image information in which the first difference is detected.

24. The image recognition method according to claim 16, wherein the predetermined range is expanded when the first determination and the second determination are continuously outside the predetermined range.

25. The image recognition method according to claim 16, wherein the predetermined range is narrowed when the first determination and the second determination are continuously within the predetermined range.

26. The image recognition method according to claim 16, wherein the predetermined range is set using the first difference between the at least a part of the first image information and the reference information.

27. The image recognition method according to claim 26, wherein the first difference and an average value of the first difference and the second difference are compared and the predetermined range is set based on the comparison.

28. A focus adjustment method in the image recognition method according to claim 16, the focus adjustment method comprising:

acquiring the first image information, the second image information, and the third image information through an optical system;

detecting a focus state of the optical system at a plurality of detection areas provided in a screen of the optical system;

selecting at least one detection area among the plurality of detection areas based on the focus state and the area recognized as corresponding to the reference image; and

performing focus adjustment of the optical system based on the focus state of the at least one detection area.

29. The focus adjustment method according to claim 28, wherein the at least one detection area is selected based on the focus state of detection area contained in the area recognized as corresponding to the reference image in the third image information.

30. An image recognition device comprising:

imaging means for acquiring first image information, second image information, and third image information;

holding means for holding reference information that functions as a reference image;

detection means for detecting a first difference between at least a part of the first image information and the reference information, detect a second difference between at least a part of the second image information and the reference information, and detect a third difference between at least a part of the third image information and the reference information;

recognition means for making a first determination whether or not the first difference is within a predetermined range, and for making a second determination whether or not the second difference is within the predetermined range;

changing means for changing the predetermined range based on the first determination and the second determination; and

the recognition means for recognizing an area corresponding to the reference image in the third image information based on the third difference and the predetermined range which has been changed.