Determination of main object on image and improvement of image quality according to main object

• US 7,668,365 B2
• Filed: 03/07/2005
• Issued: 02/23/2010
• Est. Priority Date: 03/08/2004
• Status: Active Grant

• Current Assignee: 138 East LCD Advancements Limited (Vector Capital Corporation)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Imai, Toshie
• Primary Examiner(s): Tran, Phuoc
• Application Number:
  US11/075,380
• Publication Number:
  US 20050244072A1
• Time in Patent Office: 1,814 Days
• Field of Search: 382/162, 382/164, 382/165, 382/167, 382/168, 382/170, 382/274, 382/286, 382/291
• US Class Current: 382/162
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59

Abstract

A CPU 411 splits selected image data GD into a plurality of areas (pixel data groups), analyzing the image data GD in terms of area units, and determining the color range of the areas of the image data GD. The CPU 411 determines color range areas by associating adjacent areas of the same color range when determining the color range for the areas of the image data GD. The CPU 411 acquires position data for the color range areas that have been determined. The CPU 411 acquires position conditions (main object conditions) from ROM/HDD 413, and narrows the main object candidates to “sky, green, or people.” The CPU 411 finally determines the main object by comparing the position data of the color range color areas and the position conditions corresponding to the narrowed main object.

Claims

1. An image processing device that determines the main object which characterizes an image, the image processing device comprising:

image data acquiring module that acquires image data that is data of the target image and that is composed of a plurality of pixel data;

color range determining module segmenting that segments the image data into a plurality of pixel data groups according to the plurality of areas into which the image is split, analyzes the image data in terms of pixel data units, and determines the color range exhibited by the pixel data groups;

color range area defining module that defines color range areas by associating pixel data groups that exhibit the same color range and that are adjacent to each other among pixel data groups exhibiting specific color range;

position data acquiring module that acquires position data for the color range areas;

position condition acquiring module that acquires position conditions stipulating the position where an object that corresponds to the specific color range to be present; and

main object determining module that determines the main object corresponding to the color range areas using the color range and the position data of the color range areas as well as the position conditions;

wherein each of the modules of the image processing device is executed by an integrated circuit.

2. An image processing device according to claim 1, wherein

the main object determining module determines that the main object is the sky when the color range area exhibits a sky blue color range, and the location of the color range area is an upper area in the image.

3. An image processing device according to claim 1, wherein

the main object determining module determines that the main object is vegetation when the color range area exhibits a green color range, and the location of the color range area is a lower area in the image.

4. An image processing device according to claim 1, wherein

the main object determining module determines that the main object is a person when the color range area exhibits a flesh tone color range, and the location of the color range area includes the central area of the image.

7. An image processing device according to claim 1, wherein

the areas are composed of one pixel, and the plurality of pixel data groups corresponding to the areas are composed of one pixel datum.

8. An image processing device according to claim 1, wherein

the areas are composed of a plurality of pixels, and the plurality of pixel data groups corresponding to the areas are composed of a plurality of pixel data.

9. An image processing device according to claim 1, wherein

the color range comprise at least hue as a parameter.

5. An image processing device that determines the main object which characterizes an image, the image processing device comprising:

image data acquiring module that acquires image data which is data of the target image;

image data analyzing module that segments the image data into a plurality of areas for analysis in terms of area units;

position data acquiring module that acquires position data of the areas of the image data; and

main object determining module that determines the main object using the acquired position data and the results of analysis;

wherein each of the modules of the image processing device is executed by an integrated circuit.

6. An image processing device according to claim 5, wherein

the results of analysis include information on the color range of the areas of the image data, and

the main object is determined with the use of object determining conditions stipulating the object by means of color range and location, and the position data of the areas of the image data and the color range data.

10. An image processing device that determines the main object which characterizes an image, the image processing device comprising:

image data acquiring module that acquires image data which is data of the target image and which is composed of a plurality of pixel data;

image data analyzing module that segments the image data into a plurality of pixel data groups according to the plurality of areas into which the image is split, and analyzes the image data in terms of pixel data units;

position data acquiring module that acquires position data for the pixel data groups; and

main object determining module that determines the main object using the acquired position data and results of analysis;

wherein each of the modules of the image processing device is executed by an integrated circuit.

11. An image processing device according to claim 10, wherein

the results of analysis include color range data exhibited by the pixel data groups, and

the main object determining module comprises

object identification condition acquiring module that acquires the object determination conditions that identifies objects by means of color range and location;

and

main object identifying module that identifies the main object using the position data and color range of the pixel data groups, and the acquired object identification conditions.

12. An image processing device according to claim 10, wherein

the areas are composed of one pixel, and the plurality of pixel data groups corresponding to the areas are composed of one pixel datum.

13. An image processing device according to claim 10, wherein

the areas are composed of a plurality of pixels, and the plurality of pixel data groups corresponding to the areas are composed of a plurality of pixel data.

14. An image processing device according to claim 10, wherein

the color range includes at least the hue as a parameter.

15. A method that determines the main object which characterizes an image, the method comprising:

acquiring image data which is data of the target image and which is composed of a plurality of pixel data;

segmenting the image data into a plurality of pixel data groups according to the plurality of areas into which the image is split, analyzing the image data in terms of pixel data units to obtain the color range exhibited by the pixel data groups;

defining color range areas by associating pixel data groups that exhibit the same color range among pixel data groups exhibiting specific color range;

acquiring position data for the color range areas;

acquiring position conditions stipulating the position where an object that corresponds to the specific color range to be present; and

determining the main object that characterizes the image using the color range and position data of the acquired color range areas as well as the position conditions;

wherein each of the operations of the method is executed by an integrated circuit.

16. An image processing method that determines the main object which characterizes an image, the image processing method comprising:

acquiring image data which is data of the target image;

segmenting the image data into a plurality of areas for analysis in terms of area units;

acquiring position data of the areas of the image data; and

determining the main object using the acquired position data and the results of analysis;

wherein each of the operations of the image processing method is executed by an integrated circuit.

17. An image processing method that determines the main object which characterizes an image, the image processing method comprising:

acquiring image data which is data of the target image and which is composed of a plurality of pixel data;

segmenting the image data into a plurality of pixel data groups according to the plurality of areas into which the image is split, and analyzing the image data in terms of pixel data units;

acquiring position data for the pixel data groups; and

determining the main object using the acquired position data and results of analysis;

wherein each of the operations of the image processing method is executed by an integrated circuit.

18. An image processing device comprising:

main object image data determining module that determines the main object image data corresponding to the main object characterizing the image;

property acquiring module that acquires the properties of the determined main object image data;

correction condition acquiring module that acquires correction conditions corresponding to the properties that have been acquired; and

picture quality adjusting module that adjusts the picture quality of the main object image data using the acquired correction conditions;

wherein each of the modules of the image processing device is executed by an integrated circuit.

19. An image processing device according to claim 18, wherein

the correction conditions are correction standard values corresponding to the acquired properties, and

the picture quality adjusting module adjusts the picture quality of the main object image data so as to eliminate or reduce the difference between the acquired property values and the correction standard values.

20. An image processing device according to claim 19, wherein

the main object image data is classified into a plurality of main object image data by different color range for the same main object, and

a plurality of correction standard values are prepared for each classified main object image data.

21. An image processing device according to claim 18, wherein

the main object image data is determined by segmenting the image data into a plurality of image data areas and by using the color range data and position data of the image data areas.

22. An image processing device according to claim 18, wherein

the color range has hue, saturation, and brightness parameters.

23. An image processing device for improving the picture quality of the main object characterizing an image, the image processing device comprising:

main object image data specifying module that specifies the main object image data corresponding to the main object;

color value acquiring module that acquires the color value of the specified main object image data;

main object classifying module that classifies the main object using the acquired color values;

standard color value acquiring module that acquires standard color values corresponding to the classified main object; and

picture quality adjusting module that adjusts the picture quality of the main object image data using the acquired color values and standard color values;

wherein each of the modules of the image processing device is executed by an integrated circuit.

24. An image processing device according to claim 23, wherein

the picture quality adjusting module comprises:

correction level determining module that determines the level of correction so that the difference between the color value and standard color value is eliminated or reduced; and

picture quality correcting module for applying the correction level that has been determined to the color value in order to correct the picture quality of the image data in the main object area.

25. An image processing device according to claim 24, wherein

the correction level determining module determines the correction level by a formula that is modified according to the symbols of the difference.

26. An image processing device according to claim 24, further comprising

low correction image data for using the color value as reference to determine low correction target data, among the image data, which is targeted for correction with low correction levels at ore below the correction level;

and

low correcting module that corrects the low correction target image data by applying the low correction level to the color value.

27. An image processing device according to claim 26, wherein

the low correction target data is data other than the main object image data among the image data.

28. An image processing device according to claim 23, wherein

the main object is classified into a plurality of main objects by different color range for the same main object, and

a plurality of standard color values are prepared for each classified main object.

29. An image processing device according to claim 28, wherein

the picture quality adjusting module comprises

correction level determining module that determines the level of correction, by a formula that is modified according to the type of classified main object, so that the difference between the color value and standard color value is eliminated or reduced;

and

picture quality correcting module that correct the picture quality of the image data in the main object area by applying the correction level that determined to the color value.

30. An image processing device according to claim 23, wherein

the main object image data is specified by segmenting the image data into a plurality of image data areas and by using the color range data and position data of the image data areas.

31. An image processing device according to claim 23, wherein

the color range has hue, saturation, and brightness parameters.

32. An image processing method comprising:

determining the main object image data corresponding to the main object characterizing the image;

acquiring the properties of the determined main object image data;

acquiring correction conditions corresponding to the properties that have been acquired; and

adjusting the picture quality of the main object image data using the acquired correction conditions;

wherein each of the operations of the image processing method is executed by an integrated circuit.

33. An image processing method for improving the picture quality of the main object characterizing an image, the image processing method comprising:

specifying the main object image data corresponding to the main object;

acquiring the color value of the specified main object image data;

classifying the main object using the acquired color values;

acquiring standard color values corresponding to the classified main object; and

adjusting the picture quality of the main object image data using the acquired color values and standard color values;

wherein each of the operations of the image processing method is executed by an integrated circuit.