Traitement en cours

Veuillez attendre...

Paramétrages

Paramétrages

Aller à Demande

1. WO2005013066 - AGENCEMENT LOGIQUE, STRUCTURE DE DONNEES, SYSTEME ET PROCEDE PERMETTANT UNE REPRESENTATION MULTILINEAIRE D'ENSEMBLES DE DONNEES COMBINEES AUX FINS DE SYNTHESE, DE ROTATION ET DE COMPRESSION

Note: Texte fondé sur des processus automatiques de reconnaissance optique de caractères. Seule la version PDF a une valeur juridique

[ EN ]

WHAT IS CLAIMED:

1. A data structure for generating an object descriptor of at least one object, comprising:
a plurality of first data elements including information regarding at least one characteristic of the at least one object, wherein the information of the first data elements is capable of being used to obtain the object descriptor, wherein the object descriptor is related to the at least one characteristic and a further characteristic of the at least one object, and is capable of being used to generate a plurality of second data elements which contain information regarding the further characteristic of the at least one object based on the object descriptor, wherein each of the at least one object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

2. The data structure of claim 1, wherein the at least one characteristic of the at least one object is at least one of a a viewpoint, an illumination, and a pixel.

3. The data structure of claim 1 , wherein the first data elements are defined by at least two primitives.

4. The data structure of claim 3 , wherein the primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

5. The data structure of claim 4, wherein the first data elements form a tensor organized based on the primitives.

6. The data structure of claim 1, wherein the second data elements are defined by at least two primitives.

7. The data structure of claim 1 , wherein the object descriptor is obtained using an n-mode orthonormal decomposition procedure.

8. The data structure of claim 1, wherein the second data elements are generated using a generative model.

9. A method for generating an object descriptor of at least one object, comprising the steps of:
collecting a plurality of first data elements which contain information regarding at least one characteristic of the at least one object;
obtaining the object descriptor based on the information of the first data elements, wherein the object descriptor is related to the at least one characteristic and a further characteristic of the object; and
generating a plurality of second data elements which contain information regarding the further characteristic of the at least one object based on the object descriptor, wherein each of the at least one object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

10. The method of claim 9, wherein the at least one characteristic of the at least one object is at least one of a a viewpoint, an illumination, and a pixel.

11. The method of claim 9, wherein the first data elements are defined by at least two primitives.

12. The method of claim 11 , wherein the primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

13. The method of claim 11 , wherein the first data elements form a tensor organized based on the primitives.

14. The method of claim 9, wherein the second data elements are defined by at least two primitives.

15. The method of claim 9, wherein the object descriptor is obtained using an n-mode orthonormal decomposition procedure.

16. The method of claim 9, wherein the second data elements are generated using a generative model.

17. A storage medium storing a software program that is adapted for generating an object descriptor of at least one object, wherein the software program, when executed by a processing anangement, is configured to cause the processing anangement to execute the steps comprising of:
collecting a plurality of first data elements which contain information regarding at least one characteristic of the at least one object;
obtaining the object descriptor based on the information of the first data elements, wherein the object descriptor is related to the at least one characteristic and a further characteristic of the object; and
generating a plurality of second data elements which contain information regarding the further characteristic of the at least one object based on the object descriptor, wherein each of the at least one object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

18. The storage medium of claim 17, wherein the at least one characteristic of the at least one object is at least one of a a viewpoint, an illumination, and a pixel.

19. The storage medium of claim 17, wherein the first data elements are defined by at least two primitives.

20. The storage medium of claim 19, wherein the primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

21. The storage medium of claim 19, wherein the first data elements form a tensor organized based on the primitives.

22. The storage medium of claim 17, wherein the second data elements are defined by at least two primitives.

23. The storage medium of claim 17, wherein the object descriptor is obtained using an n-mode orthonoraial decomposition procedure.

24. The storage medium of claim 17, wherein the second data elements are generated using a generative model.

25. A logic anangement for generating an object descriptor of at least one object, wherein the logic anangement is adapted for an execution by a processing anangement to perform the steps comprising of:
collecting a plurality of first data elements which contain information regarding at least one characteristic of the at least one object;
obtaining the object descriptor based on the information of the first data elements, wherein the object descriptor is related to the at least one characteristic and a further characteristic of the object; and
generating a plurality of second data elements which contain information regarding the further characteristic of the at least one object based on the object descriptor, wherein each of the at least one object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

26. The logic anangement of claim 25, wherein the at least one characteristic of the at least one object is at least one of a a viewpoint, an illumination, and a pixel.

27. The logic anangement of claim 25, wherein the first data elements are defined by at least two primitives.

28. The logic anangement of claim 27, wherein the primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

29. The logic anangement of claim 27, wherein the first data elements form a tensor organized based on the primitives.

30. The logic anangement of claim 25, wherein the second data elements are defined by at least two primitives.

31. The logic anangement of claim 25, wherein the object descriptor is obtained using an n-mode orthonormal decomposition procedure.

32. The logic anangement of claim 25, wherein the second data elements are generated using a generative model.

33. A data structure for identifying a sample object based upon a sample object descriptor, comprising:
a plurality of first data elements including information which is defined by at least two first primitives, wherein the first data elements are capable of being used to obtain at least one of a plurality of object descriptors; and
a plurality of second data elements including information which is defined by at least two second primitives, wherein the second data elements are capable of being used to obtain the sample object descriptor, and wherein the at least one of the object descriptors are configured to be compared to the sample object descriptor for determining whether the sample object descriptor is potentially identifiable as one of the object descriptors, wherein each of the plurality of object descriptors is associated with a respective one of a plurality of objects, wherein the sample object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

34. The data structure of claim 33, wherein the first primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

35. The data structure of claim 33, wherein the second primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

36. The data structure of claim 33, wherein the first data elements form a tensor organized based on the first primitives.

37. The data structure of claim 33, wherein the second data elements form a tensor organized based on the second primitives.

38. The data structure of claim 33, wherein each of the object descriptors and the sample object descriptor are obtained using an n-mode single value decomposition procedure.

39. The data structure of claim 33, wherein a magnitude of the sample object descriptor is compared to respective magnitudes of the object descriptors to determine whether the sample object is potentially identifiable as one of the objects.

40. A method for identifying a sample object based upon a sample object descriptor, comprising the steps of:
collecting a plurality of data elements which are defined by at least two primitives;
obtaining at least one of a plurality of object descriptors based on the information of the data elements; and
comparing the sample object descriptor to at least one of the object descriptors for determining whether the sample object descriptor is identifiable as one of the object descriptors, wherein each of the object descriptors is associated with a respective one of a plurality of objects, wherein the sample object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

41. The method of claim 40, wherein the first primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

42. The method of claim 40, wherein the second primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

43. The method of claim 40, wherein the first data elements form a tensor organized based on the first primitives.

44. The method of claim 40, wherein the second data elements form a tensor organized based on the second primitives.

45. The method of claim 40, wherein each of the obj ect descriptors and the sample object descriptor are obtained using an n-mode single value decomposition procedure.

46. The method of claim 40, wherein a magnitude of the sample object descriptor is compared to respective magnitudes of the object descriptors to determine whether the sample object is potentially identifiable as one of the objects.

47. A storage medium including a software program for identifying a sample object based upon a sample object descriptor, wherein the software program, when executed by a processing anangement, is configured to cause the processing anangement to execute the steps comprising of:
collecting a plurality of data elements which are defined by at least two primitives;

obtaining at least one of a plurality of object descriptors based on the information of the data elements; and
comparing the sample object descriptor to at least one of the object descriptors for determining whether the sample object descriptor is identifiable as one of the object descriptors, wherein each of the object descriptors is associated with a respective one of a plurality of objects, wherein the sample object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

48. The storage medium of claim 47, wherein the first primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

49. The storage medium of claim 47, wherein the second primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

50. The storage medium of claim 47, wherein the first data elements form a tensor organized based on the first primitives.

51. The storage medium of claim 47, wherein the second data elements form a tensor organized based on the second primitives.

52. The storage medium of claim 47, wherein each of the object descriptors and the sample object descriptor are obtained using an n-mode single value decomposition procedure.

53. The storage medium of claim 47, wherein a magnitude of the sample object descriptor is compared to respective magnitudes of the object descriptors to determine whether the sample object is potentially identifiable as one of the objects.

54. A logic anangement for identifying a sample object based upon a sample object descriptor, wherein the logic anangement is adapted for an execution by a processing anangement to perfonn the steps comprising of:
collecting a plurality of data elements which are defined by at least two primitives;
obtaining at least one of a plurality of object descriptors based on the information of the data elements; and
comparing the sample object descriptor to at least one of object descriptors for determining whether the sample object descriptor is identifiable as one of the object descriptors, wherein each of the object descriptors is associated with a respective one of a plurality of objects, wherein the sample object is one of an identity of an object, a viewpoint, an illumination, and a pixel.

55. The logic anangement of claim 54, wherein the first primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

56. The logic anangement of claim 54, wherein the second primitives include at least one of an identity of an object, a viewpoint, an illumination, and a pixel.

57. The logic arrangement of claim 54, wherein the first data elements form a tensor organized based on the first primitives.

58. The logic anangement of claim 54, wherein the second data elements form a tensor organized based on the second primitives.

59. The logic anangement of claim 54, wherein each of the object descriptors and the sample object descriptor are obtained using an n-mode single value decomposition procedure.

60. The logic anangement of claim 54, wherein a magnitude of the sample object descriptor is compared to respective magnitudes of the object descriptors to determine whether the sample object is potentially identifiable as one of the objects.

61. A method for reducing a dimensionality of one of at least two object descriptors, comprising the steps of:
collecting a plurality of data elements which are defined by at least two primitives;
obtaining the one of the object descriptors based on the information of the data elements; and
reducing the dimensionality of the one of the object descriptors, wherein each of the object descriptors except for the one of the object descriptors having the reduced dimensionality maintain full dimensionality, wherein the one of the object descriptors is one of an identity of an object, a viewpoint, an illumination, and a pixel.

62. The method of claim 61 , wherein the data elements form a tensor organized based on the primitives.

63. The method of claim 61 , wherein the one of the at least two obj ect descriptors is obtained using an n-mode single value decomposition procedure.

64. The method of claim 61 , wherein the dimensionality of the one of the object descriptors is reduced using an n-mode orthogonal iteration procedure.

65. A storage medium storing a software program for reducing a dimensionality of one of at least two object descriptors, wherein the software program, when executed by a processing anangement, is configured to cause the processing anangement to execute the steps comprising of:
collecting a plurality of data elements which are defined by at least two primitives;
obtaining the one of the object descriptors based on the information of the data elements; and
reducing the dimensionality of the one of the object descriptors, wherein the one of the object descriptors is one of an identity of an object, a viewpoint, an illumination, and a pixel.

66. The storage medium of claim 65, wherein each of the object descriptors except for the one of the object descriptors having the reduced dimensionality maintain full dimensionality.

67. The storage medium of claim 65, wherein the data elements form a tensor organized based on the primitives.

68. The storage medium of claim 65, wherein the one of the at least two object descriptors is obtained using an n-mode single value decomposition procedure.

69. The storage medium of claim 65, wherein the dimensionality of the one of the object descriptors is reduced using an n-mode orthogonal iteration procedure.

70. A logic anangement for reducing a dimensionality of one of at least two object descriptors, wherein the logic anangement is adapted for an execution by a processing anangement to perform the steps comprising of:
collecting a plurality of data elements which are defined by at least two primitives;
obtaining the one of the object descriptors based on the information of the data elements; and
reducing the dimensionality of the one of the obj ect descriptors, wherein the one of the object descriptors is one of an identity of an object, a viewpoint, an illumination, and a pixel.

71. The logic anangement of claim 70, wherein each of the object descriptors except for the one of the object descriptors having the reduced dimensionality maintain full dimensionality.

72. The logic anangement of claim 70, wherein the data elements form a tensor organized based on the primitives.

73. The logic anangement of claim 70, wherein the one of the at least two object descriptors is obtained using an n-mode single value decomposition procedure.

74. The logic anangement of claim 70, wherein the dimensionality of the one of the object descriptors is reduced using an n-mode orthogonal iteration procedure.

75. A data structure for generating an object descriptor, comprising:
a plurality of data elements which are defined by at least two primitives, wherein the information of the data elements is capable of being used to obtain the object descriptor using an orthonormal decomposition procedure, wherein the object descriptor is one of an identity of an object, a viewpoint, an illumination, and a pixel.

76. The data structure of claim 75, wherein the data elements form a tensor organized based on the primitives, and wherein the tensor has a fixed order.

77. The data structure of claim 75, wherein the n-mode orthonormal
decomposition procedure is an n-mode singular value decomposition procedure.

78. The data structure of claim 77, wherein the n-mode singular value
decomposition procedure is capable of decomposing the tensor into a core tensor and at least two orthonormal matrices.

79. The data structure of claim 75, wherein each of the primatives is one of an identity of an object, a viewpoint of the object, an illumination of the object, and a pixel of the obj ect.

80. A method for generating an object descriptor, comprising the steps of:
collecting a plurality of data elements which are defined by at least two primitives; and
obtaining the object descriptor based on the information of the data elements using an n-mode orthonormal decomposition process, wherein the object descriptor is one of an identity of an object, a viewpoint, an illumination, and a pixel.

81. The method of claim 80, wherein the data elements form a tensor organized based on the primitives, and wherein the tensor has a fixed order.

82. The method of claim 80, wherein the n-mode orthonormal decomposition procedure is an n-mode singular value decomposition procedure.

83. The method of claim 82, wherein the n-mode singular value decomposition procedure is capable of decomposing the tensor into a core tensor and at least two orthonormal matrices.

84. The method of claim 80, wherein each of the primatives is one of an identity of an object, a viewpoint of the object, an illumination of the object, and a pixel of the object.

85. A storage medium storing a software program that is adapted for generating an object descriptor, wherein the software program, when executed by a processing anangement, is configured to cause the processing anangement to execute the steps comprising of:
collecting a plurality of data elements which are defined by at least two primitives; and
obtaining the object descriptor based on the information of the data elements using an n-mode orthonormal decomposition process, wherein the object descriptor is one of an identity of an object, a viewpoint, an illumination, and a pixel.

86. The storage medium of claim 85, wherein the data elements form a tensor organized based on the primitives, and wherein the tensor has a fixed order.

87. The storage medium of claim 85, wherein the n-mode orthonormal decomposition procedure is an n-mode singular value decomposition procedure.

88. The storage medium of claim 87, wherein the n-mode singular value decomposition procedure is capable of decomposing the tensor into a core tensor and at least two orthonormal matrices.

89. The storage medium of claim 85, wherein each of the primatives is one of an identity of an object, a viewpoint of the object, an illumination of the object, and a pixel of the object.

90. A logic anangement for generating an object descriptor, wherein the logic anangement is adapted for an execution by a processing anangement to perform the steps comprising of:
collecting a plurality of data elements which are defined by at least two primitives; and
obtaining the object descriptor based on the information of the data elements using an n-mode orthonormal decomposition process, wherein the object descriptor is one of an identity of an object, a viewpoint, an illumination, and a pixel.

91. The logic anangement of claim 90, wherein the data elements form a tensor organized based on the primitives, and wherein the tensor has a fixed order.

92. The logic anangement of claim 90, wherein the n-mode orthonormal decomposition procedure is an n-mode singular value decomposition procedure.

93. The logic anangement of claim 92, wherein the n-mode singular value decomposition procedure is capable of decomposing the tensor into a core tensor and at least two orthonormal matrices.

94. The logic anangement of claim 90, wherein each of the primatives is one of an identity of an object, a viewpoint of the object, an illumination of the object, and a pixel of the object.