System and method for open space metadata-based storage and retrieval of images in an image database

• US 6,115,717 A
• Filed: 06/30/1997
• Issued: 09/05/2000
• Est. Priority Date: 01/23/1997
• Status: Expired due to Term

• Current Assignee: Eastman Kodak Company
• Original Assignee: Eastman Kodak Company
• Inventors: Romer, Donna M., Mehrotra, Rajiv, Warnick, James
• Primary Examiner(s): Black, Thomas G.
• Assistant Examiner(s): Mizrahi, Diane D.
• Application Number:
  US08/885,481
• Time in Patent Office: 1,163 Days
• Field of Search: 707/102, 707/104, 345/503, 340/825.22, 382/190, 396/56, 280/834
• US Class Current: 1/1
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system for the storage of a digital image in an image database, the system comprises: a processor; software for automatically generating with said processor open space metadata from the digital image independent of manually inputting data; and software for storing the open space metadata along with the associated image in the image database.

Claims

1. A system for the storage of a digital image in an image database, the system comprising:

(a) a processor;

(b) means for automatically generating with said processor open space metadata from the digital image independent of manually inputting data; and

(c) means for storing the open space metadata along with the associated image in the image database.

2. The system as in claim 1, wherein said processor is a programmable computer.

3. The system as in claim 2, wherein said storing means is remotely located with respect to said general purpose computer.

4. The system as in claim 2, wherein the open space metadata includes depictive properties of open space comprising color, texture, shape, orientation and location.

5. The system as in claim 4, wherein the color, texture, shape, extent and location are expressed as semantic names.

6. The system as in claim 2, wherein the open space metadata includes individually or any combination of open space extent, open space openness, open space average color and open space color range.

7. The system as in claim 6, wherein said open space extent includes spatial coordinates of a bounding shape that encompasses the identified open space.

8. The system as in claim 7, wherein said open space openness includes a percentage occupied by the open space of a bounding shape that encompasses the open space.

9. The system as in claim 8, wherein said open space average color includes individually or any combination of the average of the color component pixel values of pixels in the open space, the variance of the color component pixel values of pixels in the open space, and the skewness of the color component pixel values of pixels in the open space.

10. The system as in claim 9, wherein said open space color range includes a range of color component pixel values of the open space.

11. The system as in claim 2, wherein said generating means includes means for generating an open space map.

12. The system as in claim 11, wherein said generating means includes means for user verification of open space metadata.

13. The system as in claim 1, wherein said storing means includes indexed storage for efficient processing.

14. A system for the retrieval of images from an image database based upon the characteristics of open space in the images contained in the image database, the system comprising:

(a) a processor;

(b) means for transmitting a user specified open space search request to the processor;

(c) means for retrieving with the processor images from the image database which match the open space search request;

(d) means for automatically ranking with the processor the retrieved open space images from the image database so that images are ranked in descending order of match to the search request; and

(e) means for presenting the ranked image results of the image database query to the user.

15. The system as in claim 14, wherein said retrieving means includes retrieval by an indexed search for efficient processing.

16. The system as in claim 14 further comprising means for specifying the desired depictive properties of open space.

17. The system as in claim 16, wherein the search request includes searching on either one or all of a plurality of depictive properties of open space comprising open space extent, open space openness, open space average color and open space color range.

18. The system as in claim 17, wherein the search request includes weighting the depictive properties of open space in the search request.

19. The system as in claim 16, wherein said specifying means includes a graphical user interface for providing search parameters.

20. The system as in claim 19, wherein said graphical user interface includes a scroll bar for adjusting search parameters.

21. The system as in claim 19, wherein said graphical user interface includes means for entering a semantic name for adjusting search parameters.

22. The system as in claim 19, wherein said graphical user interface includes means for selecting color component values from a color wheel.

23. The system as in claim 19, wherein said graphical user interface includes means for selecting color component values from a region in an example image.

24. The system as in claim 14, wherein the search request includes providing an image representative of desired open space depictive properties from which open space query parameters are automatically derived.

25. The system as in claim 16, wherein said specifying means includes displaying an extent template on which the user graphically identifies open space extent.

26. The system as in claim 14, wherein said presenting means includes displaying the retrieved images in a first predetermined array ordered according to ranking.

27. The system as in claim 26, wherein said presenting means further includes means for accessing the retrieved images which were not displayed in the first predetermined array.

28. A method for the storage of a digital image in an image database, the method comprising the steps of:

(a) providing a processor;

(b) automatically generating with the processor open space metadata independent of manually inputting data; and

(c) storing the open space metadata along with the associated image in the image database.

29. The method as in claim 28, wherein step (c) indexing the storage for efficient processing.

30. The method as in claim 29, wherein the open space metadata includes depictive properties of open space comprising color, texture, shape, orientation and location.

31. The method as in claim 28, wherein step (a) includes providing a general purpose programmable computer as the processor.

32. The method as in claim 31, wherein step (c) includes remotely locating a storing means that stores the open space metadata with respect to the general purpose computer.

33. The method as in claim 31, wherein step (b) includes providing the open space metadata as either all or any of a plurality of depictive properties comprising open space extent, open space openness, open space average color and open space color range.

34. The method as in claim 33 further comprising determining coordinates of a bounding shape that encompasses the identified open space as the open space extent.

35. The method as in claim 33 further comprising determining a percentage occupied by the open space of a bounding shape that encompasses the open space as the open space openness.

36. The method as in claim 33 further comprising determining the open space average color as individually or any combination of average color components of the open space of pixels in the open space, variance of the color components of the open space of pixels in the open space, and skewness of the color components of the open space of pixels in the open space.

37. The method as in claim 33 further comprising determining the open space color range as a range of color components of the open space.

38. The method as in claim 31, wherein step (b) includes generating an open space map.

39. The method as in claim 33, wherein step (b) includes verifying the open space metadata by the user.

40. A method for retrieval of images from an image database based upon the characteristics of open space in the images contained in the image database, the method comprising the steps of:

(a) providing a processor;

(b) transmitting a user specified open space search request to the processor;

(c) retrieving with the processor images from the image database which match the open space search request;

(d) automatically ranking with said processor the retrieved open space images from the image database so that images are ranked in descending order of match to the search request; and

(e) presenting the ranked image results of the image database query to the user.

41. The method as in claim 40, wherein step (c) includes retrieving the images using an indexed search for efficient processing.

42. The method as in claim 40 wherein step (b) includes searching on either or all of a plurality of depictive parameters comprising open space extent, open space openness, open space average color and open space color range.

43. The method as in claim 42 further comprising weighting depictive properties of open space in the search request.

44. The method as in claim 40 further comprising providing an image representative of desired open space depicts properties from which open space query parameters are automatically derived as the search request.

45. The method as in claim 40 further comprising displaying an extent template on which the user graphically identifies open space extent.

46. The method as in claim 40 further comprising displaying the retrieved images in a first predetermined array ordered according to rank.

47. The method as in claim 46 further comprising accessing the retrieved images which were not displayed in the first predetermined array.

48. The method as in claim 40 further comprising providing a graphical user interface for inputting and altering search parameters.

49. The method as in claim 48 further comprising providing a scroll bar for inputting and altering search parameters.

50. The method as in claim 48 further comprising providing a semantic name for inputting and altering search parameters.

51. The method as in claim 48 further comprising providing a color wheel for inputting and altering search parameters.

52. The method as in claim 48 further comprising extracting color component values from an example image for inputting and altering search parameters.

53. A computer program product for retrieval of images from an image database based upon the characteristics of open space in the images contained in the image database, comprising:

a computer readable storage medium having a computer program stored thereon for performing the steps of;

(a) transmitting a user specified open space search request; and

(b) retrieving with the processor images from the image database which match the open space search request;

(c) automatically ranking with said processor the retrieved open space images from the image database so that images are ranked in descending order of match to the search request; and

(d) presenting the ranked image results of the image database query to the user.

54. The computer program product as in claim 53 wherein step (b) includes searching on either or all of a plurality of depictive parameters comprising open space extent, open space openness, open space average color and open space color range.

55. The computer program product as in claim 53 further comprising weighting depictive properties of open space in the search request.

56. The computer program product as in claim 53 further comprising providing an image representative of desired open space depicts properties from which open space query parameters are automatically derived as the search request.

57. The computer program product as in claim 53 further comprising displaying an extent template on which the user graphically identifies open space extent.

58. The computer program product as in claim 53 further comprising displaying the retrieved images in a first predetermined array ordered according to rank.

59. The computer program product as in claim 58 further comprising accessing the retrieved images which were not displayed in the first predetermined array.

60. The computer program product as in claim 53 further comprising providing a graphical user interface for inputting and altering search parameters.

61. The computer program product as in claim 60 further comprising providing a scroll bar for inputting and altering search parameters.

62. The computer program product as in claim 60 further comprising providing a semantic name for inputting and altering search parameters.

63. The computer program product as in claim 60 further comprising providing a color wheel for inputting and altering search parameters.

64. The computer program product as in claim 60 further comprising extracting color component values from an example image for inputting and altering search parameters.

65. A computer program product for storage of a digital image in an image database, comprising:

a computer readable storage medium having a computer program stored thereon for performing the step of;

(a) automatically generating open space metadata independent of manually inputting data; and

(b) storing the open space metadata along with the associated image in the image database.

66. The computer program product as in claim 65, wherein step (a) includes providing the open space metadata as either all or any of a plurality of depictive properties comprising open space extent, open space openness, open space average color and open space color range.

67. The computer program product as in claim 66 further comprising determining coordinates of a bounding shape that encompasses the identified open space as the open space extent.

68. The computer program product as in claim 66 further comprising determining a percentage occupied by the open space of a bounding shape that encompasses the open space as the open space openness.

69. The computer program product as in claim 66 further comprising determining the open space average color as individually or any combination of average color components of the open space of pixels in the open space, variance of the color components of the open space of pixels in the open space, and skewness of the color components of the open space of pixels in the open space.

70. The computer program product as in claim 66 further comprising determining the open space color range as a range of color components of the open space.

71. The computer program product as in claim 65, wherein step (a) includes generating an open space map.

72. The computer program product as in claim 65, wherein step (a) includes verifying the open space metadata by the user.

73. The computer program product as in claim 65, wherein the open space metadata includes depictive properties of open space comprising color, texture, shape, orientation and location.