Image pattern matching utilizing discrete curve matching with a mapping operator

• US 20030198389A1
• Filed: 10/03/2002
• Published: 10/23/2003
• Est. Priority Date: 04/10/2002
• Status: Active Grant

• Current Assignee: National Instruments Corporation (Emerson Electric Company)
• Original Assignee: National Instruments Corporation (Emerson Electric Company)
• Inventors: Nair, Dinesh, Wenzel, Lothar, Schmidt, Darren R., Crotty, Kevin M., Rajagopal, Ram, Kumar, Satish V., Fisher, Matthew S.
• Granted Patent: US 7,139,432 B2
• Time in Patent Office: Days
• US Class Current: 382/218
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors
• CPC Class Codes: G06V 10/752 Contour matching

Abstract

System and method for determining the presence of an object of interest in a target image. Regions of a target image may be located that match an object of interest, e.g., in a template image, with respect to various information, e.g., luminance, color and/or other types of boundary information. The invention includes improved methods for mapping point sequences (e.g., pixel sequences) or curves to new point sets or curves for curve matching. The method determines the presence of an object of interest in a target image despite of or using various types of topological transformations of the object of interest in the target image. One or more mapping operators are determined based on template curves and/or example target curves. Pattern matching is performed on one or more target images using the mapping operator(s) to generate pattern matching results, and the pattern matching results output.

Claims

1. A method for determining the presence of an object of interest in a target image, the method comprising:

mapping a template image discrete curve to a mapped template image discrete curve using a mapping operator;

acquiring the target image;

determining a target image discrete curve from the target image, wherein the target image discrete curve corresponds to a respective object in the target image;

performing shape matching on the mapped target image discrete curve and a mapped template image discrete curve, wherein the mapped template image discrete curve corresponds to the object of interest, wherein said performing shape matching computes a distance for the mapped target image discrete curve relative to the mapped template image discrete curve; and

generating pattern matching results based on the distances.

2. The method of claim 1,

wherein said determining the target image discrete curve from the target image comprises:

determining an initial target image discrete curve from the target image; and

mapping the initial target template discrete curve to a mapped target discrete curve using the mapping operator, wherein the mapped target discrete curve comprises the target discrete curve; and

wherein said performing curve matching on the target discrete curve and the mapped template discrete curve comprises performing curve matching on the mapped target discrete curve and the mapped template discrete curve.

3. The method of claim 1,

wherein said determining the target image discrete curve from the target image comprises performing edge detection on the target image to determine edges of objects present in the target image.

4. The method of claim 1,

wherein said determining a target image discrete curve from the target image comprises:

detecting at least one boundary present in the target image, wherein the at least one boundary corresponds to a shape of an object in the target image; and

determining the target image discrete curve from the at least one boundary.

5. The method of claim 4,

wherein the at least one boundary detected in the target image defines at least one visual boundary that is visually identifiable in the target image;

wherein the mapped target image discrete curve does not define to a visual boundary that is visually identifiable in the target image.

6. The method of claim 4,

wherein the at least one boundary detected to be present in the target image defines at least one shape that is visually identifiable in the object;

wherein the mapped target image discrete curve does not define a shape that is visually identifiable in the object.

7. The method of claim 1,

wherein the target image discrete curve defines at least one visual boundary that is visually identifiable in the target image;

wherein the mapped target image discrete curve does not define a visual boundary that is visually identifiable in the target image.

8. The method of claim 1,

wherein the target image discrete curve defines at least one shape that is visually identifiable in the target image;

wherein the mapped target image discrete curve does not define a shape that is visually identifiable in the target image.

9. The method of claim 1,

wherein said determining the target image discrete curve from the target image comprises performing boundary detection on the target image to determine boundaries of objects present in the target image.

10. The method of claim 1,

wherein said determining a target image discrete curve from the target image comprises normalizing the target image discrete curve.

11. The method of claim 10,

wherein said normalizing comprises normalizing one or more of:

energy of the target image discrete curve; and

length of the target image discrete curve.

12. The method of claim 1,

wherein said determining a target image discrete curve from the target image comprises re-sampling the target image discrete curve;

and

wherein, after said re-sampling, the target image discrete curve and the mapped template image discrete curve have the same number of points.

13. The method of claim 1,

wherein said generating curve matching results comprises generating information indicating one or more matches for an object of interest in the target image.

14. The method of claim 1,

wherein said determining comprises determining a plurality of target image discrete curves from the target image, wherein each of the plurality of target image discrete curves corresponds to a respective image object in the target image;

wherein said performing curve matching comprises performing curve matching on each of the target image discrete curves relative to the mapped template image discrete curve, wherein said performing curve matching computes a distance measure for each of the target image discrete curves relative to the mapped template image discrete curve; and

wherein said generating curve matching results comprises generating curve matching results based on the distance measures for each of the target image discrete curves.

15. The method of claim 14,

wherein said performing curve matching comprises performing curve matching on each of the target image discrete curves relative to each of a plurality of mapped template image discrete curves, wherein said performing curve matching computes a distance measure for each of the target image discrete curves relative to each of the mapped template image discrete curves;

and

wherein said generating curve matching results comprises generating curve matching results based on the distance measures for each of the target image discrete curves.

16. The method of claim 1,

wherein the discrete curves comprise sequences of pixels.

17. The method of claim 16,

wherein the target image is interpretable as a complex plane;

wherein the discrete curves comprise sequences of pixels; and

wherein positions of said pixels comprise complex values.

18. The method of claim 1, further comprising:

characterizing an object of interest to produce the mapped template image discrete curve.

19. The method of claim 18, wherein said characterizing the object of interest is performed prior to said acquiring the target image.

20. The method of claim 18, wherein said characterizing the object of interest comprises:

determining a template image discrete curve from information regarding the object of interest, wherein the template image discrete curve corresponds to the object of interest;

mapping the template image discrete curve to the mapped template image discrete curve using the mapping operator.

21. The method of claim 20,

wherein the information regarding the object of interest comprises a template image containing the object of interest.

22. The method of claim 20, further comprising:

analyzing one or more example target images to determine one or more example target image discrete curves, wherein each of the one or more example target image discrete curves corresponds to an image object or part of an image object in the one or more example target images; and

determining the mapping operator based on the determined template image discrete curve and the one or more example target image discrete curves.

23. The method of claim 22, wherein said determining the mapping operator comprises:

normalizing the template image discrete curve and the one or more example target image discrete curves; and

computing a weight vector W, such that

${〈<br><br>c_n,c_m〉<br><br>}_{W_m}=\underset{i=1}{\overset{N}{\sum <br><br>}}<br><br>c_{n<br><br>\text{\hspace{1em}<br><br>}<br><br>i}<br><br>c_{m<br><br>\text{\hspace{1em}<br><br>}<br><br>i}^{*}<br><br>W_i={\mathrm{\delta <br><br>}}_{n<br><br>\text{\hspace{1em}<br><br>}<br><br>m}$

wherein c_m comprises the normalized template discrete curve and wherein c_n comprises any one of the one or more example target discrete curves; and

wherein δ

_nm is the Kronecker delta.

24. The method of claim 20, further comprising:

analyzing the mapped template image discrete curve and one or more example target image discrete curves generated from one or more example target images to determine at least one parameter for the mapping operator; and

configuring the mapping operator according to the determined at least one parameter.

25. The method of claim 24,

wherein the at least one parameter is used to increase a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to objects that are not of interest.

26. The method of claim 20,

wherein the distance between the target image discrete curve and the mapped template image discrete curve is greater than a distance computed between the target image discrete curve and the template image discrete curve.

27. The method of claim 1,

wherein the target image discrete curve characterizes one or more discrete curves;

and

wherein the mapped template image discrete curve characterizes one or more discrete curves.

28. The method of claim 1,

wherein the template image discrete curve characterizes a first shape;

and

wherein the mapped template image discrete curve characterizes a second shape.

29. The method of claim 1,

wherein said mapping the template image discrete curve to the mapped template image discrete curve comprises:

applying said mapping operator to each point in the template image discrete curve to generate corresponding points in the mapped template image discrete curve.

30. The method of claim 1,

wherein the mapping operator is used to enhance a distance between mapped discrete curves corresponding to an object of interest and mapped discrete curves corresponding to objects that are not of interest.

31. The method of claim 1, further comprising:

receiving first information regarding an object of interest;

receiving second information regarding one or more objects that are not of interest;

determining at least one parameter for the mapping operator based on the first information and the second information, wherein the at least one parameter is determined to enhance a distance between mapped discrete curves corresponding to an object of interest and mapped discrete curves corresponding to the one or more objects that are not of interest; and

configuring the mapping operator according to the determined at least one parameter.

32. The method of claim 1,

wherein the mapping operator is a weighting operator.

33. The method of claim 1,

wherein the mapping operator operates to emphasize differences between respective objects corresponding to respective discrete curves.

34. The method of claim 1,

wherein the mapped template image discrete curve is a unique discrete curve generated from the template image discrete curve.

35. The method of claim 1,

wherein the mapped template image discrete curve is more stable to image disturbances than the template image discrete curve.

36. The method of claim 1,

wherein the mapping operator includes one or more terms that are computable for different objects of interest.

37. The method of claim 1,

wherein the mapping operator includes one or more terms that are computable to enhance differences between respective objects of interest and objects not of interest.

38. The method of claim 1,

wherein the mapping operator comprises a weight vector w;

wherein the template image discrete curve comprises a first vector;

wherein said weight vector w, and said first vector have the same number of elements; and

wherein said mapping the template image discrete curve to the mapped template image discrete curve comprises;

multiplying each element of the weight vector w with corresponding elements in the first vector to generate a second vector, wherein elements of the second vector comprise the mapped template image discrete curve.

39. The method of claim 1, further comprising:

outputting said curve matching results.

40. A method for determining the presence of an object of interest in a target image, the method comprising:

mapping a template image discrete curve to a mapped template image discrete curve using a mapping operator, wherein the mapped template image discrete curve corresponds to an object of interest;

acquiring the target image;

determining a plurality of target image discrete curves from the target image, wherein each of the target image discrete curves corresponds to a respective object in the target image;

for each of the target image discrete curves, mapping the target image discrete curve to a mapped target image discrete curve using a mapping operator;

performing shape matching on each of the mapped target image discrete curves and a mapped template image discrete curve corresponding to the object of interest, wherein said performing shape matching computes a distance for the each of the mapped target image discrete curves relative to the mapped template image discrete curve; and

generating pattern matching results based on the distances.

41. The method of claim 40,

wherein said determining the one or more target image discrete curves from the target image comprises:

determining one or more initial target image discrete curves from the target image; and

mapping the one or more initial target image discrete curves to a respective one or more mapped target image discrete curves using the respective mapping operators, wherein the one or more mapped target image discrete curves comprises the one or more target image discrete curves; and

wherein said performing curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curve comprises performing curve matching between each of the one or more mapped target image discrete curves and the one or more mapped template image discrete curves.

42. A method for performing curve matching, the method comprising:

mapping the one or more template image discrete curves to one or more mapped template image discrete curves using respective operators, wherein the one or more mapped template image discrete curves are different from the one or more template image discrete curves, and wherein the one or more mapped template image discrete curves are generated based on an object of interest;

acquiring a target image; and

determining one or more target image discrete curves from the target image, wherein the one or more target image discrete curves represents an image object in the target image;

performing curve matching between one or more target image discrete curves and the one or more mapped template image discrete curves, wherein said performing curve matching computes a distance measure for the one or more target image discrete curves relative to the one or more mapped template image discrete curves; and

generating curve matching results based on the distance measures.

43. The method of claim 42,

wherein said determining the one or more target image discrete curves from the target image comprises:

determining one or more initial target image discrete curves from the target image; and

mapping the one or more initial target image discrete curves to a respective one or more mapped target image discrete curves using the respective mapping operators, wherein the one or more mapped target image discrete curves comprises the one or more target image discrete curves; and

wherein said performing curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curve comprises performing curve matching between each of the one or more mapped target image discrete curves and the one or more mapped template image discrete curves.

44. A method for determining the presence of an object of interest in a target image, the method comprising:

mapping a first shape to a different second shape using an operator, wherein the second shape is different from the first shape, and wherein the second shape is generated based on the object of interest;

acquiring the target image;

determining one or more third shapes from the target image, wherein each of the one or more third shapes represents a respective image object in the target image;

performing curve matching between each of the third shapes and the second shape, wherein said performing curve matching computes a distance measure for each of the third shapes relative to the second shape; and

generating curve matching results based on the distance measures.

45. The method of claim 44,

wherein said determining the one or more third shapes from the target image comprises:

determining one or more initial target shapes from the target image; and

mapping the one or more initial target shapes to a respective one or more mapped target shapes using the operator, wherein the one or more mapped target shapes comprise the one or more third shapes; and

wherein said performing curve matching between each of the third shapes and the second shape comprises performing curve matching on each of the one or more mapped target shapes and the second shape.

46. A method for matching discrete curves, comprising:

determining a mapping operator based on a template image;

performing curve matching on one or more target images using the mapping operator to generate curve matching results; and

outputting the curve matching results.

47. A carrier medium which stores program instructions for determining the presence of an object of interest in a target image, wherein the program instructions are executable to perform:

mapping a template image discrete curve to a mapped template image discrete curve using a mapping operator;

acquiring the target image;

determining a target image discrete curve from the target image, wherein the target image discrete curve corresponds to a respective object in the target image;

performing curve matching on the target image discrete curve and the mapped template image discrete curve, wherein the mapped template image discrete curve corresponds to the object of interest, wherein said performing curve matching computes a distance for the target image discrete curve relative to the mapped template image discrete curve; and

generating pattern matching results based on the distances.

48. The carrier medium of claim 47,

wherein said determining the target image discrete curve from the target image comprises:

determining an initial target image discrete curve from the target image; and

mapping the initial target image discrete curve to a mapped target image discrete curve using the mapping operator, wherein the mapped target image discrete curves comprises the target image discrete curve; and

wherein said performing curve matching between the target image discrete curve and the mapped template image discrete curve comprises performing curve matching between the mapped target image discrete curve and the mapped template image discrete curve.

49. The carrier medium of claim 47,

wherein said determining the target image discrete curve from the target image comprises performing boundary detection on the target image to determine boundaries of objects present in the target image.

50. The carrier medium of claim 47,

wherein said determining a target image discrete curve from the target image comprises:

detecting at least one boundary present in the target image, wherein the at least one boundary corresponds to a shape of an object in the target image; and

determining the target image discrete curve from the at least one boundary.

51. The carrier medium of claim 47,

wherein said determining a target image discrete curve from the target image comprises normalizing the target image discrete curve.

52. The carrier medium of claim 51,

wherein said normalizing comprises normalizing one or more of:

energy of the target image discrete curve; and

length of the target image discrete curve.

53. The method of claim 47,

wherein said determining a target image discrete curve from the target image comprises re-sampling the target image discrete curve;

and

wherein, after said re-sampling, the target image discrete curve and the mapped template image discrete curve have the same number of points.

54. The carrier medium of claim 47,

wherein said determining the target image discrete curve from the target image comprises:

determining an initial target image discrete curve from the target image; and

mapping the initial target image discrete curve to a mapped target image discrete curve using the mapping operator, wherein the mapped target image discrete curve comprises the target image discrete curve; and

wherein said performing curve matching on the target image discrete curve and the mapped template image discrete curve comprises performing curve matching on the mapped target image discrete curve and the mapped template image discrete curve.

55. The carrier medium of claim 47,

wherein said generating curve matching results comprises generating information indicating one or more matches for an object of interest in the target image.

56. The carrier medium of claim 47,

wherein said determining comprises determining a plurality of target image discrete curves from the target image, wherein each of the plurality of target image discrete curves corresponds to a respective image object in the target image;

wherein said performing curve matching comprises performing curve matching on each of the target image discrete curves relative to the mapped template image discrete curve, wherein said performing curve matching computes a distance measure for each of the target image discrete curves relative to the mapped template image discrete curve; and

wherein said generating curve matching results comprises generating curve matching results based on the distance measures for each of the target image discrete curves.

57. The carrier medium of claim 56,

wherein said performing curve matching comprises performing curve matching on each of the target image discrete curves relative to each of a plurality of mapped template image discrete curves, wherein said performing curve matching computes a distance measure for each of the target image discrete curves relative to each of the mapped template image discrete curves;

and

wherein said generating curve matching results comprises generating curve matching results based on the distance measures for each of the target image discrete curves.

58. The carrier medium of claim 47,

wherein the discrete curves comprise sequences of pixels.

59. The carrier medium of claim 58,

wherein the target image is interpretable as a complex plane;

wherein the discrete curves comprise sequences of pixels; and

wherein positions of said pixels comprise complex values.

60. The carrier medium of claim 47, wherein the program instructions are further executable to perform:

characterizing an object of interest to produce the mapped template image discrete curve.

61. The carrier medium of claim 60, wherein said characterizing the object of interest is performed prior to said acquiring the target image.

62. The carrier medium of claim 60, wherein said characterizing the object of interest comprises:

determining a template image discrete curve from information regarding the object of interest, wherein the template image discrete curve corresponds to the object of interest;

mapping the template image discrete curve to the mapped template image discrete curve using the mapping operator.

63. The carrier medium of claim 62,

wherein the information regarding the object of interest comprises a template image containing the object of interest.

64. The carrier medium of claim 62, wherein the program instructions are further executable to perform:

analyzing one or more example target images to determine one or more example target image discrete curves, wherein each of the one or more example target image discrete curves corresponds to an image object or part of an image object in the one or more example target images; and

determining the mapping operator based on the determined template image discrete curve and the one or more example target image discrete curves.

65. The carrier medium of claim 64, wherein said determining the mapping operator comprises:

normalizing the template image discrete curve and the one or more example target image discrete curves; and

computing a weight vector W, such that

${〈<br><br>c_n,c_m〉<br><br>}_{W_m}=\underset{i=1}{\overset{N}{\sum <br><br>}}<br><br>c_{\mathrm{ni}}<br><br>c_{\mathrm{mi}}^{*}<br><br>W_i={\mathrm{\delta <br><br>}}_{\mathrm{nm}}$

wherein c_m comprises the normalized template discrete curve and wherein c_n comprises any one of the one or more example target discrete curves; and

wherein δ

_nm is the Kronecker delta.

66. The carrier medium of claim 62, wherein the program instructions are further executable to perform:

analyzing the mapped template image discrete curve and one or more example target image discrete curves generated from one or more example target images to determine at least one parameter for the mapping operator; and

configuring the mapping operator according to the determined at least one parameter.

67. The carrier medium of claim 66,

wherein the at least one parameter is used to increase a distance between mapped sequences corresponding to the object of interest and mapped discrete curves corresponding to objects that are not of interest.

68. The carrier medium of claim 62,

wherein the distance between the target image discrete curve and the mapped template image discrete curve is greater than a distance computed between the target image discrete curve and the template image discrete curve.

69. The carrier medium of claim 47,

wherein the target image discrete curve characterizes one or more discrete curves;

and

wherein the mapped template image discrete curve characterizes one or more discrete curves.

70. The carrier medium of claim 47,

wherein the template image discrete curve characterizes a first shape;

and

wherein the mapped template image discrete curve characterizes a second shape.

71. The carrier medium of claim 47,

wherein said mapping the template image discrete curve to the mapped template image discrete curve comprises:

applying said mapping operator to each point in the template image discrete curve to generate corresponding points in the mapped template image discrete curve.

72. The carrier medium of claim 47,

wherein the mapping operator is used to enhance a distance between mapped discrete curves corresponding to an object of interest and mapped discrete curves corresponding to objects that are not of interest.

73. The carrier medium of claim 47, wherein the program instructions are further executable to perform:

receiving first information regarding an object of interest;

receiving second information regarding one or more objects that are not of interest;

determining at least one parameter for the mapping operator based on the first information and the second information, wherein the at least one parameter is determined to enhance a distance between mapped discrete curves corresponding to an object of interest and mapped discrete curves corresponding to the one or more objects that are not of interest; and

configuring the mapping operator according to the determined at least one parameter.

74. The carrier medium of claim 47,

wherein the mapping operator is a weighting operator.

75. The carrier medium of claim 47,

wherein the mapping operator operates to emphasize differences between respective objects corresponding to respective discrete curves.

76. The carrier medium of claim 47,

wherein the mapped template image discrete curve is a unique discrete curve generated from the template image discrete curve.

77. The carrier medium of claim 47,

wherein the mapped template image discrete curve is more stable to image disturbances than the template image discrete curve.

78. The carrier medium of claim 47,

wherein the mapping operator includes one or more terms that are computable for different objects of interest.

79. The carrier medium of claim 47,

wherein the mapping operator includes one or more terms that are computable to enhance differences between respective objects of interest and objects not of interest.

80. The carrier medium of claim 47,

wherein the mapping operator comprises a weight vector w;

wherein the template image discrete curve comprises a first vector;

wherein said weight vector w, and said first vector have the same number of elements; and

wherein said mapping the template image discrete curve to the mapped template image discrete curve comprises;

multiplying each element of the weight vector w with corresponding elements in the first vector to generate a second vector, wherein elements of the second vector comprise the mapped template image discrete curve.

81. The carrier medium of claim 47, wherein the program instructions are further executable to perform:

;

outputting said curve matching results.

82. A carrier medium which stores program instructions for performing curve matching between target image discrete curves and a template image discrete curve, wherein the program instructions are executable to perform:

mapping a template image discrete curve to a mapped template image discrete curve using a mapping operator, wherein the mapped template image discrete curve corresponds to an object of interest;

acquiring a target image; and

determining the plurality of target image discrete curves from the target image, wherein each of the target image discrete curves corresponds to a respective object in the target image. for each of the plurality of target image discrete curves, performing curve matching on the target image discrete curve and the mapped template image discrete curve, wherein said performing curve matching computes a distance for the each of the target image discrete curves relative to the mapped template image discrete curve; and

generating curve matching results based on the distances.

83. The carrier medium of claim 82,

wherein said determining the plurality of target image discrete curves from the target image comprises:

determining a plurality of initial target image discrete curves from the target image; and

mapping the plurality of initial target image discrete curves to a respective plurality of mapped target image discrete curves using the mapping operator, wherein the plurality of mapped target image discrete curves comprises the plurality of target image discrete curves; and

wherein said performing curve matching on each of the target image discrete curves and the mapped template image discrete curve comprises performing curve matching on each of the mapped target image discrete curve and the mapped template image discrete curve.

84. A carrier medium which stores program instructions for performing curve matching between target image discrete curves and a template image discrete curve, wherein the program instructions are executable to perform:

mapping one or more template image discrete curves to one or more mapped template image discrete curves using an operator, wherein the one or more mapped template image discrete curves are different from the one or more template image discrete curves, and wherein the one or more mapped template image discrete curves are generated based on an object of interest;

acquiring a target image;

determining the one or more target image discrete curves from the target image, wherein the one or more target image discrete curves represents an image object in the target image;

performing curve matching between one or more target image discrete curves and the one or more mapped template image discrete curves, wherein said performing curve matching computes a distance measure for the one or more target image discrete curves relative to the one or more mapped template image discrete curves; and

generating curve matching results based on the distance measures.

85. The carrier medium of claim 84,

wherein said determining the one or more target image discrete curves from the target image comprises:

determining one or more initial target image discrete curves from the target image; and

mapping the one or more initial target image discrete curves to a respective one or more mapped target image discrete curves using the respective mapping operators, wherein the one or more mapped target image discrete curves comprises the one or more target image discrete curves; and

wherein said performing curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curve comprises performing curve matching between each of the one or more mapped target image discrete curves and the one or more mapped template image discrete curves.

86. A carrier medium which stores program instructions for determining the presence of an object of interest in a target image, wherein the program instructions are executable to perform:

mapping a first shape to a different second shape using an operator, wherein the second shape is different from the first shape, and wherein the second shape is generated based on the object of interest;

acquiring the target image;

determining one or more third shapes from the target image, wherein each of the one or more third shapes represents a respective image object in the target image;

performing curve matching between each of the third shapes and the second shape, wherein said performing curve matching computes a distance measure for each of the third shapes relative to the second shape; and

generating curve matching results based on the distance measures.

87. The carrier medium of claim 86,

wherein said determining the one or more third shapes from the target image comprises:

determining one or more initial target shapes from the target image; and

mapping the one or more initial target shapes to a respective one or more mapped target shapes using the operator, wherein the one or more mapped target shapes comprise the one or more third shapes; and

wherein said performing curve matching between each of the third shapes and the second shape comprises performing curve matching on each of the one or more mapped target shapes and the second shape.

88. A carrier medium which stores program instructions for matching discrete curves, wherein the program instructions are executable to perform:

determining a mapping operator based on a template image;

performing curve matching on one or more target images using the mapping operator to generate curve matching results; and

outputting the curve matching results.

89. A system for determining the presence of an object of interest in a target image, the system comprising:

a computer system, comprising;

a processor; and

a memory medium coupled to the processor; and

an image acquisition device coupled to the processor and the memory medium;

wherein the image acquisition device is operable to;

acquire the target image; and

wherein the memory medium stores program instructions which are executable by the processor to;

map a template image discrete curve to a mapped template image discrete curve using a mapping operator;

determine a plurality of target image discrete curves from the target image, wherein each of the target image discrete curves corresponds to a respective object in the target image;

for each of the target image discrete curves, perform curve matching on each of the mapped target image discrete curves and the mapped template image discrete curve corresponding to the object of interest, wherein said performing curve matching computes a distance for the each of the mapped target image discrete curves relative to the mapped template image discrete curve; and

generate curve matching results based on the distances.

90. The system of claim 89,

wherein, in determining the plurality of target image discrete curves from the target image, the program instructions are further executable by the processor to:

determine a plurality of initial target image discrete curves from the target image; and

map the plurality of initial target image discrete curves to a respective plurality of mapped target image discrete curves using the mapping operator, wherein the plurality of mapped target image discrete curves comprises the plurality of target image discrete curves; and

wherein, in performing curve matching on each of the target image discrete curves and the mapped template image discrete curve, the program instructions are further executable by the processor to;

perform curve matching on each of the mapped target image discrete curves and the mapped template image discrete curve.

91. A system for determining the presence of an object of interest in a target image, the system comprising:

a computer system, comprising;

a processor; and

a memory medium coupled to the processor; and

an image acquisition device coupled to the processor and the memory medium;

wherein the image acquisition device is operable to;

acquire the target image; and

wherein the memory medium stores program instructions which are executable by the processor to;

map one or more template image discrete curves to one or more mapped template image discrete curves using respective operators, wherein the one or more mapped template image discrete curves are different from the one or more template image discrete curves;

determine one or more target image discrete curves from the target image, wherein the one or more target image discrete curves represents an image object in the target image;

perform curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curves, wherein the one or more mapped template image discrete curves are generated based on the object of interest, wherein said performing curve matching computes a distance measure for the one or more target image discrete curves relative to the one or more mapped template image discrete curves; and

generate curve matching results based on the distance measures.

92. The system of claim 91,

wherein, in determining the one or more target image discrete curves from the target image, the program instructions are further executable by the processor to:

determine one or more initial target image discrete curves from the target image; and

map the one or more initial target image discrete curves to a respective one or more mapped target image discrete curves using the respective operators, wherein the one or more mapped target image discrete curves comprises the one or more target image discrete curves; and

wherein, in performing curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curves, the program instructions are further executable by the processor to;

perform curve matching between each of the one or more mapped target image discrete curves and the one or more mapped template image discrete curves.

93. A system for determining the presence of an object of interest in a target image, the system comprising:

a computer system, comprising;

a processor; and

a memory medium coupled to the processor; and

an image acquisition device coupled to the processor and the memory medium;

wherein the image acquisition device is operable to;

acquire the target image; and

wherein the memory medium stores program instructions which are executable by the processor to;

mapping a first shape to different second shape using an operator, wherein the second shape is different from the first shape;

determining one or more third shapes from the target image, wherein each of the one or more third shapes represents a respective image object in the target image;

performing curve matching between the second shape and each of the third shapes, wherein the second shape is generated based on the object of interest, wherein said performing curve matching computes a distance measure for each of the third shapes relative to the second shape; and

generating curve matching results based on the distance measures.

94. The system of claim 93,

wherein, in determining the one or more third shapes from the target image, the program instructions are further executable by the processor to:

determine one or more initial target shapes from the target image; and

map the one or more initial target shapes to a respective one or more mapped target shapes using the operator, wherein the one or more mapped target shapes comprise the one or more third shapes; and

wherein, in performing curve matching between the second shape and each of the third shapes, the program instructions are further executable by the processor to;

perform curve matching on each of the one or more mapped target shapes and the second shape.

95. A system for matching discrete curves, the system comprising:

a computer system, comprising;

a processor; and

a memory medium coupled to the processor;

wherein the memory medium stores program instructions which are executable by the processor to;

determine a mapping operator based on a template image;

perform pattern matching on one or more target images using the mapping operator to generate curve matching results; and

output the curve matching results.

96. A system for matching discrete curves, the system comprising:

means for determining a mapping operator based on a template image;

means for performing pattern matching on one or more target images using the mapping operator to generate curve matching results; and

means for outputting the curve matching results.

97. A system for determining the presence of an object of interest in a target image, the system comprising:

means for mapping a template image discrete curve to a mapped template image discrete curve using a mapping operator;

means for acquiring the target image;

means for determining a target image discrete curve from the target image, wherein the target image discrete curve corresponds to a respective object in the target image;

means for performing curve matching on the target image discrete curve and the mapped template image discrete curve, wherein the mapped template image discrete curve corresponds to the object of interest, wherein said performing curve matching computes a distance for the target image discrete curve relative to the mapped template image discrete curve; and

means for generating curve matching results based on the distances.

98. The system of claim 97,

wherein said determining the target image discrete curve from the target image comprises:

determining an initial target image discrete curve from the target image; and

mapping the initial target image discrete curve to a mapped target image discrete curve using the mapping operator, wherein the mapped target image discrete curve comprises the target image discrete curve; and

wherein said performing curve matching on the target image discrete curve and the mapped template image discrete curve comprises performing curve matching on the mapped target image discrete curve and the mapped template image discrete curve.

99. A system for determining the presence of an object of interest in a target image, the system comprising:

means for mapping a template image discrete curve to a mapped template image discrete curve using a mapping operator;

means for acquiring the target image;

means for determining a plurality of target image discrete curves from the target image, wherein each of the target image discrete curves corresponds to a respective object in the target image;

means for performing curve matching on each of the target image discrete curves and the mapped template image discrete curve corresponding to the object of interest, wherein said performing curve matching computes a distance for the each of the target image discrete curves relative to the mapped template image discrete curve; and

means for generating curve matching results based on the distances.

100. The system of claim 99,

wherein said determining the plurality of target image discrete curves from the target image comprises:

determining a plurality of initial target image discrete curves from the target image; and

mapping the plurality of initial target image discrete curves to a respective plurality of mapped target image discrete curves using the mapping operator, wherein the plurality of mapped target image discrete curves comprises the plurality of target image discrete curves; and

wherein said performing curve matching on each of the target image discrete curves and the mapped template image discrete curve comprises performing curve matching on each of the mapped target image discrete curves and the mapped template image discrete curve.

101. A system for determining the presence of an object of interest in a target image, the system comprising:

means for mapping one or more template image discrete curves to one or more mapped template image discrete curves using a respective one or more operators, wherein the one or more mapped template image discrete curves are different from the one or more template image discrete curves;

means for acquiring the target image;

means for determining one or more target image discrete curves from the target image, wherein the one or more target image discrete curves represent an image object in the target image;

means for performing curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curves, wherein the one or more mapped template image discrete curves are generated based on the object of interest, wherein said performing curve matching computes a distance measure for the one or more target image discrete curves relative to the one or more mapped template image discrete curves; and

means for generating curve matching results based on the distance measures.

102. The system of claim 101,

wherein, said determining the one or more target image discrete curves from the target image comprises:

determining one or more initial target image discrete curves from the target image; and

mapping the one or more initial target image discrete curves to respective one or more mapped target image discrete curves using the respective one or more operators, wherein the one or more mapped target image discrete curves comprise the one or more target image discrete curves; and

wherein performing curve matching between the one or more target image discrete curves and the one or more mapped template image discrete curves comprises;

performing curve matching between each of the one or more mapped target image discrete curves and the one or more mapped template image discrete curves.

103. A method for characterizing an object of interest for a pattern matching application, the method comprising:

receiving data containing the object of interest;

determining a template image discrete curve from the data, wherein the template image discrete curve corresponds to the object of interest in the data; and

mapping the template image discrete curve to a mapped template image discrete curve using a mapping operator;

wherein the mapped template image discrete curve is useable to perform pattern matching to locate instances of the object of interest in acquired target data.

104. The method of claim 103,

wherein the mapping operator is a weighting operator.

105. The method of claim 103,

wherein the mapping operator operates to emphasize differences between respective image objects.

106. The method of claim 103, further comprising:

analyzing the object of interest and one or more example target images to determine one or more terms for the mapping operator;

wherein the mapping operator comprises a weight vector; and

wherein said mapping comprises;

applying the weight vector terms respectively to corresponding points in the template image discrete curve.

107. The method of claim 103, further comprising:

analyzing the object of interest and one or more example target images to determine at least one parameter for the mapping operator; and

configuring the mapping operator according to the determined at least one parameter;

wherein said mapping uses the configured mapping operator.

108. The method of claim 107,

wherein the at least one parameter is used to create a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to objects that are not of interest.

109. The method of claim 103, further comprising:

receiving first information regarding the object of interest;

receiving second information regarding one or more objects that are not of interest;

determining at least one parameter for the mapping operator based on the first information and the second information; and

configuring the mapping operator according to the determined at least one parameter.

110. The method of claim 109,

wherein the at least one parameter is used to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to objects that are not of interest.

111. The method of claim 103,

wherein said determining the template image discrete curve from the data comprises performing edge detection on the data to determine one or more edges of the object of interest present in the data.

112. The method of claim 111, further comprising:

determining a plurality of template image discrete curves from the data by performing edge detection on the data to determine a plurality of edges of the object of interest present in the data, wherein the plurality of template image discrete curves are based on the plurality of edges of the object of interest.

113. A carrier medium which stores program instructions for characterizing an object of interest for a pattern matching application, wherein the program instructions are executable to perform:

receiving data containing the object of interest;

determining a template image discrete curve from the data, wherein the template image discrete curve corresponds to the object of interest in the data; and

mapping the template image discrete curve to a mapped template image discrete curve using a mapping operator;

wherein the mapped template image discrete curve is useable to perform pattern matching to locate instances of the object of interest in acquired target data.

114. The carrier medium of claim 113,

wherein the mapping operator is a weighting operator.

115. The carrier medium of claim 113,

wherein the mapping operator operates to emphasize differences between respective image objects.

116. The carrier medium of claim 113, wherein the program instructions are further executable to perform:

analyzing the object of interest and one or more example target images to determine one or more terms for the mapping operator;

wherein the mapping operator comprises a weight vector; and

wherein said mapping comprises;

applying the weight vector terms respectively to corresponding points in the template image discrete curve.

117. The carrier medium of claim 113, wherein the program instructions are further executable to perform:

analyzing the object of interest and one or more example target images to determine at least one parameter for the mapping operator; and

configuring the mapping operator according to the determined at least one parameter;

wherein said mapping uses the configured mapping operator.

118. The carrier medium of claim 117,

wherein the at least one parameter is used to create a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to objects that are not of interest.

119. The carrier medium of claim 113, wherein the program instructions are further executable to perform:

receiving first information regarding the object of interest;

receiving second information regarding one or more objects that are not of interest;

determining at least one parameter for the mapping operator based on the first information and the second information; and

configuring the mapping operator according to the determined at least one parameter.

120. The carrier medium of claim 119,

wherein the at least one parameter is used to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to objects that are not of interest.

121. The carrier medium of claim 113,

wherein said determining the template image discrete curve from the data comprises performing edge detection on the data to determine one or more edges of the object of interest present in the data.

122. The carrier medium of claim 121, wherein the program instructions are further executable to perform:

determining a plurality of template image discrete curves from the data by performing edge detection on the data to determine a plurality of edges of the object of interest present in the data, wherein the plurality of template image discrete curves are based on the plurality of edges of the object of interest.

123. A system for characterizing an object of interest for a pattern matching application, the system comprising:

a computer system, comprising;

a processor; and

a memory medium coupled to the processor; and

wherein the memory medium stores program instructions which are executable by the processor to;

receiving data containing the object of interest;

determining a template image discrete curve from the data, wherein the template image discrete curve corresponds to the object of interest in the data; and

mapping the template image discrete curve to a mapped template image discrete curve using a mapping operator;

wherein the mapped template image discrete curve is useable to perform pattern matching to locate instances of the object of interest in acquired target data.

124. A method for characterizing an object of interest for a pattern matching application, the method comprising:

receiving first information regarding the object of interest;

determining one or more template image discrete curves from the first information, wherein the one or more template image discrete curves correspond to the object of interest in a template image; and

mapping the one or more template image discrete curves to a corresponding one or more mapped template image discrete curves using a mapping operator;

wherein the one or more mapped template image discrete curves are useable to perform pattern matching to locate instances of the object of interest in acquired target data.

125. The method of claim 124, further comprising:

receiving second information regarding objects not of interest;

determining one or more background object discrete curves from the second information, wherein the one or more background object discrete curves correspond to one or more objects not of interest; and

computing the mapping operator from the one or more template image discrete curves and the one or more background object discrete curves;

wherein the mapping operator operates to amplify differences between each of the discrete curves.

126. The method of claim 125,

wherein said first information comprises a template data which includes the object of interest;

and

wherein the second information comprises information of the one or more objects not of interest.

127. The method of claim 126,

wherein said information of the one or more objects not of interest is comprised in one or more example target images.

128. The method of claim 126,

wherein said information of the one or more objects not of interest is comprised in the template data.

129. A carrier medium which stores program instructions for characterizing an object of interest for a pattern matching application, wherein the program instructions are executable to perform:

receiving first information regarding the object of interest;

determining one or more template image discrete curves from the first information, wherein the one or more template image discrete curves correspond to the object of interest in a template image; and

mapping the one or more template image discrete curves to a corresponding one or more mapped template image discrete curves using a mapping operator;

wherein the one or more mapped template image discrete curves are useable to perform pattern matching to locate instances of the object of interest in acquired target data.

130. The carrier medium of claim 129, wherein the program instructions are further executable to perform:

receiving second information regarding objects not of interest;

determining one or more background object discrete curves from the second information, wherein the one or more background object discrete curves correspond to one or more objects not of interest; and

computing the mapping operator from the one or more template image discrete curves and the one or more background object discrete curves;

wherein the mapping operator operates to amplify differences between each of the discrete curves.

131. The carrier medium of claim 129,

wherein said first information comprises a template data which includes the object of interest;

and

wherein the second information comprises information of the one or more objects not of interest.

132. The carrier medium of claim 129,

wherein said information of the one or more objects not of interest is comprised in one or more example target images.

133. The carrier medium of claim 129,

wherein said information of the one or more objects not of interest is comprised in the template data.

134. A system for characterizing an object of interest for a pattern matching application, the system comprising:

a computer system, comprising;

a processor; and

a memory medium coupled to the processor; and

wherein the memory medium stores program instructions which are executable by the processor to;

receive first information regarding the object of interest;

determine one or more template image discrete curves from the first information, wherein the one or more template image discrete curves correspond to the object of interest in a template image; and

map the one or more template image discrete curves to a corresponding one or more mapped template image discrete curves using a mapping operator;

wherein the one or more mapped template image discrete curves are useable to perform pattern matching to locate instances of the object of interest in acquired target data.