System and method for making a correction to a plurality of images

• US 7,653,246 B2
• Filed: 05/27/2004
• Issued: 01/26/2010
• Est. Priority Date: 11/18/2003
• Status: Expired due to Fees

• Current Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Kitagawara, Atsushi, Hibi, Yoshiharu, Okutsu, Masaru
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): BLOOM, NATHAN J
• Application Number:
  US10/854,642
• Publication Number:
  US 20050105821A1
• Time in Patent Office: 2,070 Days
• Field of Search: 382/170, 382/190, 382/203
• US Class Current: 382/195
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 7/66 of image moments or centre of gravity
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80

Abstract

An image processing apparatus includes a feature amount recognition unit that recognizes a feature amount of each of plural pieces of image data, and a processing reference extraction unit that extracts a processing reference for image correction to be made to the plural pieces of image data from the feature amount recognized by the feature amount recognition unit.

Claims

1. An image processing method comprising:

inputting a plurality of pieces of image data into an input unit of an image processing apparatus;

using a recognizing unit of the image processing apparatus to recognize a geometrical feature amount of a main subject of each of the plurality of pieces of image data input through the input unit;

using a correction unit of the image processing apparatus to set a processing reference for image correction to be made to the respective main subjects, based on the geometrical feature amounts recognized by the recognizing unit;

making the image correction to the main subject of each of the plural pieces of input image data, using the set processing reference; and

outputting each of the plural pieces of image data in which the correction has been made to the main subjects, wherein

the recognizing includes extracting a rectangle that circumscribes each main subject,

the setting sets the processing reference based on the extracted circumscribing rectangles,

the recognizing comprises calculating sizes of the circumscribing rectangles based on the extracted circumscribing rectangles, and

the making correction comprises setting a target value of a size, as the processing reference, based on an average value of the calculated sizes, and making the correction to the main subjects of the respective digital images using the target value.

2. An image processing apparatus comprising:

a geometrical feature amount recognition unit that recognizes a main subject of each of a plurality of pieces of image data from each image data and extracts a geometrical feature amount of each recognized main subject;

a processing reference extraction unit that extracts a processing reference for image correction to be made to the plurality of pieces of image data, based on the plurality of geometrical feature amounts extracted by the geometrical feature amount recognition unit; and

an image correction unit that makes the image correction to each of the plurality of pieces of image data using the processing reference extracted by the processing reference extraction unit, wherein

the geometrical feature amount recognition unit extracts a rectangle that circumscribes each main subject,

the processing reference extraction unit extracts the processing reference from the extracted circumscribing rectangles,

the geometrical feature amount recognition unit calculates circumscribing start positions of the circumscribing rectangles, and

the processing reference extraction unit sets a target value of a circumscribing start position, as the processing reference, based on the respective circumscribing start positions of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

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

the geometrical feature amount recognition unit calculates sizes of the main subjects based on the extracted circumscribing rectangles, and

the processing reference extraction unit sets a target value of a size, as the processing reference, based on the sizes of the respective main subjects of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

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

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the processing reference extraction unit sets a target value of a position of a center of gravity, as the processing reference, based on the centers of gravity of the respective main subjects of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

8. The image processing apparatus according to claim 4, wherein

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the processing reference extraction unit sets a target value of a position of a center of gravity, as the processing reference, based on the centers of gravity of the respective main subjects of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

3. An image processing apparatus comprising:

a geometrical feature amount recognition unit that recognizes a main subject of each of a plurality of pieces of image data from each image data and extracts a geometrical feature amount of each recognized main subject;

a processing reference extraction unit that extracts a processing reference for image correction to be made to the plurality of pieces of image data, based on the plurality of geometrical feature amounts extracted by the geometrical feature amount recognition unit; and

an image correction unit that makes the image correction to each of the plurality of pieces of image data using the processing reference extracted by the processing reference extraction unit, wherein

the geometrical feature amount recognition unit extracts a rectangle that circumscribes each main subject,

the processing reference extraction unit extracts the processing reference from the extracted circumscribing rectangles,

the geometrical feature amount recognition unit calculates sizes of the main subjects based on the extracted circumscribing rectangles, and

the processing reference extraction unit sets a target value of a size, as the processing reference, based on the sizes of the respective main subjects of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

7. The image processing apparatus according to claim 3, wherein

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the processing reference extraction unit sets a target value of a position of a center of gravity, as the processing reference, based on the centers of gravity of the respective main subjects of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

5. An image processing apparatus comprising:

a geometrical feature amount recognition unit that recognizes a main subject of each of a plurality of pieces of image data from each image data and extracts a geometrical feature amount of each recognized main subject;

a processing reference extraction unit that extracts a processing reference for image correction to be made to the plurality of pieces of image data, based on the plurality of geometrical feature amounts extracted by the geometrical feature amount recognition unit; and

an image correction unit that makes the image correction to each of the plurality of pieces of image data using the processing reference extracted by the processing reference extraction unit, wherein

the geometrical feature amount recognition unit extracts a rectangle that circumscribes each main subject,

the processing reference extraction unit extracts the processing reference from the extracted circumscribing rectangles,

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the processing reference extraction unit sets a target value of a position of a center of gravity, as the processing reference, based on the centers of gravity of the respective main subjects of the plurality of pieces of image data calculated by the geometrical feature amount recognition unit.

9. An image processing apparatus comprising:

an input unit that inputs a plurality of digital images;

a geometrical feature amount recognition unit that recognizes a geometrical feature amount of a main subject from each of the plurality of digital images input through the input unit; and

a geometrical correction unit that makes a correction to the main subjects of the respective digital images so that the images are geometrically unified, based on the geometrical feature amounts recognized by the feature amount recognition unit, wherein

the geometrical feature amount recognition unit extracts contours of the main subjects, extracts rectangles that circumscribe the main subjects based on the extracted contours and recognizes the geometrical feature amounts based on the extracted circumscribing rectangles, wherein

the geometrical feature amount recognition unit calculates circumscribing start positions of the circumscribing rectangles based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a circumscribing start position, as the processing reference, based on an average value of the respective circumscribing start positions of the plurality of digital images calculated by the geometrical feature amount recognition unit, and make the correction to the main subjects of the respective digital images using the target value.

11. The image processing apparatus according to claim 9, wherein

the geometrical feature amount recognition unit calculates sizes of the circumscribing rectangles based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a size, as the processing reference, based on an average value of the calculated sizes, and make the correction to the main subjects of the respective digital images using the target value.

13. The image processing apparatus according to claim 9, wherein

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a center of gravity, as the processing reference, based on an average value of the centers of gravity of the respective main subjects of the plurality of digital images calculated by the geometrical feature amount recognition unit, and make the correction to the main subjects of the respective digital images using the target value.

15. The image processing apparatus according to claim 11, wherein

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a center of gravity, as the processing reference, based on an average value of the centers of gravity of the respective main subjects of the plurality of digital images calculated by the geometrical feature amount recognition unit, and make the correction to the main subjects of the respective digital images using the target value.

10. An image processing apparatus comprising:

an input unit that inputs a plurality of digital images;

a geometrical feature amount recognition unit that recognizes a geometrical feature amount of a main subject from each of the plurality of digital images input through the input unit; and

a geometrical correction unit that makes a correction to the main subjects of the respective digital images so that the images are geometrically unified, based on the geometrical feature amounts recognized by the feature amount recognition unit, wherein

the geometrical feature amount recognition unit extracts contours of the main subjects, extracts rectangles that circumscribe the main subjects based on the extracted contours and recognizes the geometrical feature amounts based on the extracted circumscribing rectangles, wherein

the geometrical feature amount recognition unit calculates sizes of the circumscribing rectangles based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a size, as the processing reference, based on an average value of the calculated sizes, and make the correction to the main subjects of the respective digital images using the target value.

14. The image processing apparatus according to claim 10, wherein

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a center of gravity, as the processing reference, based on an average value of the centers of gravity of the respective main subjects of the plurality of digital images calculated by the geometrical feature amount recognition unit, and make the correction to the main subjects of the respective digital images using the target value.

12. An image processing apparatus comprising:

an input unit that inputs a plurality of digital images;

a geometrical feature amount recognition unit that recognizes a geometrical feature amount of a main subject from each of the plurality of digital images input through the input unit; and

a geometrical correction unit that makes a correction to the main subjects of the respective digital images so that the images are geometrically unified, based on the geometrical feature amounts recognized by the feature amount recognition unit, wherein

the geometrical feature amount recognition unit extracts contours of the main subjects, extracts rectangles that circumscribe the main subjects based on the extracted contours and recognizes the geometrical feature amounts based on the extracted circumscribing rectangles, wherein

the geometrical feature amount recognition unit calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the geometrical correction unit sets a target value of a center of gravity, as the processing reference, based on an average value of the centers of gravity of the respective main subjects of the plurality of digital images calculated by the geometrical feature amount recognition unit, and make the correction to the main subjects of the respective digital images using the target value.

16. A computer-readable medium storing a program of instructions executable by a computer to perform a function for processing an image, the function comprising:

recognizing a main subject in each of a plurality of pieces of image data input;

recognizing a geometrical feature amount of each of the recognized main subjects;

setting a processing reference for image correction to be made to the respective main subjects, based on the recognized geometrical feature amounts; and

making the image correction to the main subject of each of the plural pieces of image data, using the set processing reference, wherein

the recognizing includes extracting a rectangle that circumscribes each main subject,

the setting sets the processing reference based on the extracted circumscribing rectangles,

the recognizing calculates circumscribing start positions of the circumscribing rectangles based on the extracted circumscribing rectangles, and

the image correction making sets a target value of a circumscribing start position, as the processing reference, based on an average value of the respective circumscribing start positions of the plurality of digital images calculated by the recognizing, and makes the correction to the main subjects of the respective digital images using the target value.

17. A computer-readable medium storing a program of instructions executable by a computer to perform a function for processing an image, the function comprising:

recognizing a main subject in each of a plurality of pieces of image data input;

recognizing a geometrical feature amount of each of the recognized main subjects;

setting a processing reference for image correction to be made to the respective main subjects, based on the recognized geometrical feature amounts; and

making the image correction to the main subject of each of the plural pieces of image data, using the set processing reference, wherein

the recognizing includes extracting a rectangle that circumscribes each main subject,

the setting sets the processing reference based on the extracted circumscribing rectangles,

the recognizing calculates sizes of the circumscribing rectangles based on the extracted circumscribing rectangles, and

the image correction making sets a target value of a size, as the processing reference, based on an average value of the respective sizes of the plurality of digital images calculated by the recognizing, and makes the correction to the main subjects of the respective digital images using the target value.

18. A computer-readable medium storing a program of instructions executable by a computer to perform a function for processing an image, the function comprising:

recognizing a main subject in each of a plurality of pieces of image data input;

recognizing a geometrical feature amount of each of the recognized main subjects;

setting a processing reference for image correction to be made to the respective main subjects, based on the recognized geometrical feature amounts; and

making the image correction to the main subject of each of the plural pieces of image data, using the set processing reference, wherein

the recognizing includes extracting a rectangle that circumscribes each main subject,

the setting sets the processing reference based on the extracted circumscribing rectangles,

the recognizing calculates centers of gravity of the main subjects based on the extracted circumscribing rectangles, and

the image correction making sets a target value of a center of gravity, as the processing reference, based on an average value of the centers of gravity of the respective main subjects of the plurality of digital images calculated by the recognizing, and makes the correction to the main subjects of the respective digital images using the target value.