System and method for automatically cropping graphical images

• US 7,034,848 B2
• Filed: 01/05/2001
• Issued: 04/25/2006
• Est. Priority Date: 01/05/2001
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Sobol, Robert E.
• Primary Examiner(s): Nguyen, Kimbinh T.
• Application Number:
  US09/755,715
• Publication Number:
  US 20020089516A1
• Time in Patent Office: 1,936 Days
• Field of Search: 382/118, 382/165, 382/190, 382/282, 382/291, 382/292, 345/419, 345/421, 345/620
• US Class Current: 345/620
• CPC Class Codes: H04N 1/2104 for one or a few pictures
• CPC Class Codes: H04N 1/3872 Repositioning or masking
• CPC Class Codes: H04N 5/262 Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
• CPC Class Codes: H04N 5/2621 Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability

Abstract

An image cropping system utilizes memory, an object detector, and an image cropper. A set of digital data that defines a graphical image is stored in the memory. The object detector analyzes the set of digital data and automatically identifies a portion of the digital data that defines an image of a particular object. The image cropper then uses the identified portion to determine a position of the object image within the graphical image. Based on the position of the object image within the graphical image, the image cropper automatically crops the digital data. In this regard, the position of the object image within the graphical image serves as a reference for determining which portions of the set of digital data should be cropped.

Claims

1. A system for automatically cropping graphical images, comprising:

memory for storing digital data that defines a graphical image captured by said system;

an object detector configured to perform a search of said digital data for an object of a particular type; and

an image cropper configured to automatically identify, based on said search, at least one object of said particular type within said graphical image as an object of interest based on a position of said at least one object within said graphical image but not based on any other graphical image captured by said system, said image cropper further configured to automatically perform a cropping operation on said graphical image such that said at least one object identified as an object of interest is moved closer to a center of said graphical image.

2. The system of claim 1, wherein said at least one object is an image of a person'"'"'s face, and wherein said object detector is configured to search said digital data for facial images.

3. The system of claim 1, wherein said cropping operation is based on a size of said at least one object.

4. The system of claim 1, wherein said cropping operation is performed such that said at least one object is substantially centered between two edges of said graphical image.

5. The system of claim 1, further comprising:

an input device for receiving an input from a user; and

a system manager configured to enable said image cropper based on said user input.

6. The system of claim 1, further comprising an image capturing device configured to receive an image of a scene and to produce said digital data based on said image received by said image capturing device.

7. The system of claim 6, wherein said image capturing device includes a lens for receiving said image of said scene and an image converter for producing said digital data based on said image of said scene.

8. The system of claim 1, wherein said image cropper is configured to identify said at least one object as an object of interest based on whether said at least one object is located close to a center of said graphical image.

9. A system for automatically cropping graphical images, comprising:

memory for storing digital data that defines a graphical image;

an object detector configured to analyze said digital data and to automatically identify a graphical object within said graphical image; and

an image cropper configured to make a determination as to whether said a graphical object is close to an edge of said graphical image and to automatically identify, based on said determination, said graphical object as an object to be removed from said graphical image and to automatically crop said digital data based on said determination such that said graphical object is removed from said graphical image.

10. The system of claim 9, wherein said graphical object is an image of a face.

11. A system for automatically cropping graphical images, comprising:

means for capturing graphical images;

memory for storing digital data that defines a graphical image captured by said capturing means;

means searching said digital data for an object of a particular type; and

means for automatically cropping said graphical image, said cropping means configured to automatically identify, based on said searching means, at least one object of said particular type within said graphical image as an object of interest based on a position of said at least one object image within said graphical image but not based on any other graphical image captured by said capturing means, said cropping means configured to crop said graphical image such that said at least one object identified as an object of interest is moved closer to a center of said graphical image.

12. The system of claim 11, wherein said at least one object is an image of a person'"'"'s face, and wherein said searching means is configured to search said digital data for facial images.

13. The system of claim 11, wherein said cropping means crops said graphical image based on a size of said at least one object.

14. The system of claim 11, wherein said cropping crops said graphical image such that said at least one object is substantially centered between two edges of said graphical image.

15. The system of claim 11, further comprising:

means for receiving an input from a user; and

means for enabling said cropping means based on said user input.

16. The system of claim 11, further comprising a means for receiving an image of a scene and for producing said digital data based on said image received by said receiving means.

17. A method for automatically cropping graphical images, comprising:

capturing a graphical image;

storing digital data that defines said graphical image;

automatically searching said digital data for an object of a particular type;

automatically identifying, based on said searching, at least one object of said particular type as an object of interest based on a position of said at least one object within said graphical image but not based on any captured image other than said graphical image; and

automatically cropping said graphical image based on said identifying such that said at least one object identified as an object of interest is substantially centered between at least two edges of said graphical image.

18. The method of claim 17, wherein said at least one object comprises an image of a person'"'"'s face.

19. The method of claim 17, wherein said cropping is further based on a size of said at least one object.

20. The method of claim 17, wherein said searching and cropping are automatically performed in response to said storing.

21. The method of claim 17, further comprising:

receiving an input from a user; and

enabling said cropping based on said user input.

22. The method of claim 17, further comprising enabling a user to select the type of automatic cropping to be performed in said cropping.

23. The method of claim 17, further comprising making a determination as to whether said at least one object is a facial image, wherein said cropping is based on said determination.

24. The method of claim 17, further comprising determining an extent that said at least one object is from a center region of said graphical image, wherein said identifying is based on said determining.

25. A system for automatically cropping graphical images, comprising:

an image capturing device configured to capture graphical images;

memory for storing digital data that defines a graphical image captured by said image capturing device;

an object detector configured to automatically detect a face within said graphical image; and

an image cropper configured to make a determination as to whether said face is within a particular region of said graphical image and to automatically identify said face as an object of interest based on said determination if said face is within said particular region, said image cropper further configured to automatically perform a cropping operation on said graphical image such that said face is moved closer to a center of said graphical image if said face is determined to be an object of interest, wherein said cropping operation is not based on any image captured by said image capturing device other than said graphical image.

26. The system of claim 25, wherein said object detector is further configured to detect a second face in said graphical image, and wherein said image cropper is configured to perform said cropping operation such that said second face is removed from said graphical image.

27. A method for automatically cropping graphical images, comprising:

storing digital data that defines a graphical image;

detecting a plurality of faces within said graphical image;

determining an extent that at least one of said faces is from a center region of said graphical image;

automatically identifying, based on said determining, said at least one face as an object of interest if said at least one face is within or close to said center region; and

automatically cropping said graphical image based on said identifying such that said at least one face is substantially centered within said graphical image.

28. The method of claim 27, wherein said cropping comprises removing, from said graphical image, at least one of said faces that is not identified as an object of interest.

29. A method for cropping a graphical image, comprising:

detecting a plurality of faces in the graphical image;

determining if at least one of the faces is close to a center of the graphical image;

automatically selecting one of the faces to remain in the graphical image and one of the faces for removal from the graphical image based on the determining; and

automatically cropping the graphical image based on said selecting such that the face selected for removal is removed from the graphical image.

30. The method of claim 29, further comprising determining a location in the graphical image of each of the plurality of faces.

31. The method of claim 29, wherein the cropping the graphical image comprises positioning one of the plurality of faces closer to the center.

32. The method of claim 29, wherein the cropping is performed such that said face selected to remain in the graphical image is moved closer to the center.

33. A method for cropping a graphical image, comprising:

detecting a face in a digital image of a picture; and

automatically cropping the digital image based on a size of the face relative to the digital image,

wherein the automatically cropping further comprises moving the face away from a center of the picture.

34. A system for automatically cropping graphical images, comprising:

memory for storing digital data that defines a graphical image;

an object detector configured to detect a plurality of objects of a particular type within said graphical image; and

an image cropper configured to make a determination as to whether at least one of said objects is close to a center of said graphical image and to automatically identify, based on said determination, said at least one object as an object of interest if said at least object is located close to said center, said image cropper further configured to crop said graphical image such that said at least one object is substantially centered within said graphical image.

35. The system of claim 34, wherein said objects of a particular type are facial images, and wherein said object detector is configured to search said graphical image for facial images to detect said objects of said particular type.

36. The system of claim 34, wherein said image cropper is configured to automatically remove at least one of said detected objects that is not identified as an object of interest by said image cropper.

37. A method for automatically cropping graphical images, comprising:

detecting an object within said graphical image;

determining whether said object is close to an edge of said graphical image;

selecting said object for removal from said graphical image based on said determining if said determining indicates that said object is close to said edge; and

automatically removing said object from said graphical image based on said selecting.

38. The method of claim 37, wherein said object is a face and said method further comprises searching said graphical image for facial images.

39. The method of claim 37, further comprising displaying said graphical image after said removing.

40. A method for cropping a graphical image, comprising:

detecting a face in a digital image of a picture; and

automatically cropping the digital image based on a position of the face within the digital image,

wherein the automatically cropping further comprises moving the face away from a center of the picture.