Image processing apparatus and method, image capturing apparatus and program

Patent metadata

Field	Value
Publication number	US-9390466-B2
Application number	US-201313914365-A
Country	US
Kind code	B2
Filing date	Jun 10, 2013
Priority date	Sep 8, 2008
Publication date	Jul 12, 2016
Grant date	Jul 12, 2016

Abstract

The present invention relates to an image processing apparatus and method, an image capturing apparatus, and a program which make it possible to crop an image with an optimal composition even for a subject other than a person.
A composition pattern setting section 33 sets a composition pattern corresponding to an input image, on the basis of the number of salient regions to which attention is directed in the input image, and the scene of the input image. On the basis of the composition pattern set by the composition pattern setting section 33 , a composition analyzing section 34 determines a crop region in the input image which is optimal for an image to be cropped in the composition pattern from the input image. The present invention is applicable to, for example, an image processing apparatus that adjusts the composition of a captured image.

First claim

The invention claimed is:

1. An image processing apparatus comprising:
a composition setting section configured to set a composition pattern corresponding to an input image, on the basis of the number of regions to which attention is directed in the input image, and a scene category of the input image, wherein the input image is classified into one of a predetermined scene categories; and
a crop region determining section configured to determine at least one of a plurality of crop regions in the input image which is optimal for an image to be cropped in the composition pattern from the input image, on the basis of the composition pattern.

2. The image processing apparatus according to claim 1 , further comprising a crop region selecting section configured to select a crop region from the plurality of crop regions.

3. The image processing apparatus according to claim 2 , further comprising a cropping section configured to crop the selected crop region from the input age.

4. The image processing apparatus according to claim 2 , wherein the crop region selecting section is configured to select the crop region so that a center position of a smallest rectangular region including all of the regions to which attention is directed in the input image approaches a center of the selected crop region in the input image.

5. The image processing apparatus according to claim 4 , wherein the crop region selecting section is configured to select the crop region so that the crop region becomes larger, and that a common region between the smallest rectangular region and the selected crop region becomes larger.

6. The image processing apparatus according to claim 2 , wherein the crop region selecting section is configured to select the crop region so that the selected crop region does not lie off the input image.

7. The image processing apparatus according to claim 2 , further comprising:
a panorama determining section configured to determine whether or not the input image is a panoramic image, by comparing an aspect ratio of the input image with a predetermined threshold, and
wherein the crop region selecting section selects the crop region from the plurality of crop regions on the basis of the composition pattern, in case the input image is determined as a panoramic image.

8. The image processing apparatus according to claim 2 , further comprising:
an information adding section configured to add information indicating the crop region selected by the crop region selecting section, to the input image as EXIF information.

9. The image processing apparatus according to claim 1 , further comprising:
a region extracting section configured to extract each of the regions to which attention is directed in the input image; and
a scene classifying section configured to classify the input image into one of the predetermined scene categories.

10. The image processing apparatus according to claim 1 , further comprising a user interface for selecting a composition pattern by a user.

11. The image processing apparatus according to claim 1 , further comprising:
a scene classifying section configured to classify the input image into one of the predetermined scene categories based on a feature quantity obtained from a frequency conversion on the input image.

12. The image processing apparatus according to claim 1 , further comprising a user interface for selecting a crop region among the plurality of crop regions provided as candidates of crop region.

13. An image processing method comprising:
setting a composition pattern corresponding to an input image, on the basis of the number of regions to which attention is directed in the input image, and a scene category of the input image, wherein the input image is classified into one of a predetermined scene categories; and
determining a plurality of crop regions in the input image which is optimal for an image to be cropped in the composition pattern from the input image, on the basis of the composition pattern.

14. The image processing method according to claim 13 , further comprising selecting a crop region from the plurality of crop regions.

15. The image processing method according to claim 14 , further comprising cropping the selected crop region from the input image.

16. The image processing method according to claim 14 , further comprising:
determining whether or not the input image is a panoramic image, by comparing an aspect ratio of the input image with a predetermined threshold, and
selecting the crop region comprises selecting the crop region on the basis of the composition pattern, if it is judged that the input image is a panoramic image.

17. The image processing method according to claim 14 , further comprising:
adding information indicating the selected crop region to the input image as EXIF information.

18. The image processing method according to claim 13 , further comprising:
extracting each of the regions to which attention is directed in the input image; and
classifying the input image into one of the predetermined scene categories.

19. The image processing method according to claim 13 , further comprising selecting the crop region so that a center position of a smallest rectangular region including all of the regions to which attention is directed in the input image approaches a center of the selected crop region in the input image.

20. The image processing method according to claim 19 , further comprising selecting the crop region so that the selected crop region becomes larger, and a common region between the smallest rectangular region and the selected crop region becomes larger.

21. The image processing method according to claim 13 , further comprising selecting the crop region so that the selected crop region does not lie off the input image.

22. The image processing method according to claim 13 , further comprising providing a user interface for selecting a composition pattern by a user.

23. The image processing method according to claim 13 , further comprising:
classifying the input image into one of the predetermined scene categories based on a feature quantity obtained from a frequency conversion on the input image.

Assignees

• Sony Corp

Inventors

• Nakamura Yusuke
• Gomi Shinichiro
• Masuno Tomonori
• Suzuki Masaru

Classifications

• H04N23/64

  Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image · CPC title

• H04N23/635

  Region indicators; Field of view indicators · CPC title

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• H04N23/61

  based on recognised objects · CPC title

• H04N23/80

  Camera processing pipelines; Components thereof · CPC title