Pattern matching utilizing discrete curve matching with multiple mapping operators

• US 20030194133A1
• Filed: 10/03/2002
• Published: 10/16/2003
• 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 7,133,538 B2
• Time in Patent Office: Days
• US Class Current: 382/209
• 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 10/752 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 sets 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. A plurality of mapping operators are determined based on template curves and/or example target curves, e.g., background object curves. Pattern matching is performed on one or more target images using the mapping operators 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 data set, the method comprising:

determining an object of interest discrete curve from information regarding the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

mapping the object of interest discrete curve to a first mapped object of interest discrete curve using a first mapping operator configured according to a first set of terms;

mapping the object of interest discrete curve to a second mapped object of interest discrete curve using a second mapping operator configured according to a second set of terms;

acquiring the target data set;

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

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

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

generating pattern matching results based on the distances.

2. The method of claim 1,

wherein the first set of terms is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a first class of one or more objects that are not of interest;

wherein the second set of terms is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a second class of one or more objects that are not of interest.

3. The method of claim 2, further comprising:

receiving information regarding the object of interest;

receiving information regarding the first class of one or more objects that are not of interest;

determining the first mapping operator based on the information regarding the object of interest and the information regarding the first class of one or more objects that are not of interest;

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

determining the second mapping operator based on the information regarding the object of interest and the information regarding the second class of one or more objects that are not of interest.

4. The method of claim 1, wherein said determining the target discrete curve from the target data set comprises:

determining an initial target discrete curve from the target data set;

mapping the initial target discrete curve to a first mapped target discrete curve using the first mapping operator; and

mapping the initial target discrete curve to a second mapped target discrete curve using the second mapping operator;

wherein said performing curve matching on the first mapped object of interest discrete curve and the target discrete curve comprises;

performing curve matching on the first mapped object of interest discrete curve and the first mapped target discrete curve; and

wherein said performing curve matching on the second mapped object of interest discrete curve and the target discrete curve comprises;

performing curve matching on the second mapped object of interest discrete curve and the second mapped target discrete curve.

5. The method of claim 1, further comprising:

analyzing the distances generated from the first mapped target discrete curve and the distances generated from the second mapped target discrete curve.

6. The method of claim 5,

wherein the first set of terms and the second set of terms are 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.

7. The method of claim 6,

wherein the distance between the first mapped target discrete curve and the first mapped object of interest discrete curve is greater than a distance computed between the target discrete curve and the object of interest discrete curve;

and

wherein the distance between the second mapped target discrete curve and the second mapped object of interest discrete curve is greater than a distance computed between the target discrete curve and the object of interest discrete curve.

8. The method of claim 1, further comprising:

analyzing one or more example target data sets to determine a plurality of example target discrete curves, wherein at least one of the plurality of example target discrete curves corresponds to a data object or part of a data object of a first class in the one or more example target data sets, and wherein at least one of the plurality of example target discrete curves corresponds to a data object of a second class in the one or more example target data sets; and

determining the first and second mapping operators based on the object of interest discrete curve and the plurality of example target discrete curves.

9. The method of claim 8, wherein the first and second mapping operators correspond to the first and second class, respectively, and wherein said determining the first and second mapping operators comprises, for each mapping operator:

normalizing the object of interest discrete curve and the plurality of example target discrete curves; and

computing a weight vector W, such that

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

wherein c_n comprises the normalized object of interest discrete curve and c_m comprises any of the one or more normalized example target discrete curves of the respective class; and

wherein δ

_nm is the Kronecker delta.

10. The method of claim 1, further comprising:

outputting said pattern matching results.

11. The method of claim 1,

wherein the target data set comprises a target image;

wherein the object of interest comprises an image object; and

wherein the target discrete curve comprises a target image discrete curve.

12. The method of claim 11, further comprising:

receiving a template image, wherein the template image includes the object of interest;

wherein said determining the object of interest discrete curve from information regarding the object of interest comprises determining the object of interest discrete curve from the template image.

13. The method of claim 12, further comprising:

receiving one or more images containing one or more objects of the first class that are not of interest;

determining the first mapping operator based on the template image and the one or more images containing the one or more objects of the first class that are not of interest;

receiving one or more images containing one or more objects of the second class that are not of interest; and

determining the first mapping operator based on the template image and the one or more images containing the one or more objects of the second class that are not of interest.

14. A carrier medium which stores program instructions for determining the presence of an object of interest in a target data set, wherein the program instructions are executable by a processor to perform:

determining an object of interest discrete curve from information regarding the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

mapping the object of interest discrete curve to a first mapped object of interest discrete curve using a first mapping operator configured according to a first set of terms;

mapping the object of interest discrete curve to a second mapped object of interest discrete curve using a second mapping operator configured according to a second set of terms;

acquiring the target data set;

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

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

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

generating pattern matching results based on the distances.

15. The carrier medium of claim 14,

wherein the first mapping operator is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a first class of one or more objects that are not of interest;

wherein the second mapping operator is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a second class of one or more objects that are not of interest.

16. The carrier medium of claim 15, wherein the program instructions are further executable to perform:

receiving information regarding the object of interest;

receiving information regarding the first class of one or more objects that are not of interest;

determining the first mapping operator based on the information regarding the object of interest and the information regarding the first class of one or more objects that are not of interest;

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

determining the second mapping operator based on the information regarding the object of interest and the information regarding the second class of one or more objects that are not of interest.

17. The carrier medium of claim 14, wherein said determining the target discrete curve from the target data set comprises:

determining an initial target discrete curve from the target data set;

mapping the initial target discrete curve to a first mapped target discrete curve using the first mapping operator; and

mapping the initial target discrete curve to a second mapped target discrete curve using the second mapping operator;

wherein said performing curve matching on the first mapped object of interest discrete curve and the target discrete curve comprises;

performing curve matching on the first mapped object of interest discrete curve and the first mapped target discrete curve; and

wherein said performing curve matching on the second mapped object of interest discrete curve and the target discrete curve comprises;

performing curve matching on the second mapped object of interest discrete curve and the second mapped target discrete curve.

18. The carrier medium of claim 14, wherein the program instructions are further executable to perform:

analyzing the distances generated from the first mapped target discrete curve and the distances generated from the second mapped target discrete curve.

19. The carrier medium of claim 18,

wherein the first set of terms and the second set of terms are 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.

20. The carrier medium of claim 19,

wherein the distance between the first mapped target discrete curve and the first mapped object of interest discrete curve is greater than a distance computed between the target discrete curve and the object of interest discrete curve;

and

wherein the distance between the second mapped target discrete curve and the second mapped object of interest discrete curve is greater than a distance computed between the target discrete curve and the object of interest discrete curve.

21. The carrier medium of claim 14, wherein the program instructions are further executable to perform:

analyzing one or more example target data sets to determine a plurality of example target discrete curves, wherein at least one of the plurality of example target discrete curves corresponds to a data object or part of a data object of a first class in the one or more example target data sets, and wherein at least one of the plurality of example target discrete curves corresponds to a data object of a second class in the one or more example target data sets; and

determining the first and second mapping operators based on the object of interest discrete curve and the plurality of example target discrete curves.

22. The carrier medium of claim 21, wherein the first and second mapping operators correspond to the first and second class, respectively, and wherein said determining the first and second mapping operators comprises, for each mapping operator:

normalizing the object of interest discrete curve and the plurality of example target discrete curves; and

computing a weight vector W, such that

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

wherein c_n comprises the normalized object of interest discrete curve and c_m comprises any of the one or more normalized example target discrete curves of the respective class; and

wherein δ

_nm is the Kronecker delta.

23. The carrier medium of claim 14, wherein the program instructions are further executable to perform:

outputting said pattern matching results.

24. The carrier medium of claim 14,

wherein the target data set comprises a target image;

wherein the object of interest comprises an image object; and

wherein the target discrete curve comprises a target image discrete curve.

25. The carrier medium of claim 24, wherein the program instructions are further executable to perform:

receiving a template image, wherein the template image includes the object of interest;

wherein said determining the object of interest discrete curve from information regarding the object of interest comprises determining the object of interest discrete curve from the template image.

26. The carrier medium of claim 25, wherein the program instructions are further executable to perform:

receiving one or more images containing one or more objects of the first class that are not of interest;

determining the first mapping operator based on the template image and the one or more images containing the one or more objects of the first class that are not of interest;

receiving one or more images containing one or more objects of the second class that are not of interest; and

determining the first mapping operator based on the template image and the one or more images containing the one or more objects of the second class that are not of interest.

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

a computer system, comprising;

a processor; and

a memory medium coupled to the processor; and

a data acquisition device coupled to the processor and the memory medium;

wherein the data acquisition device is operable to;

acquire a target data set; and

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

determine an object of interest discrete curve from information regarding the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

map the object of interest discrete curve to a first mapped object of interest discrete curve using a first mapping operator configured according to a first set of terms;

map the object of interest discrete curve to a second mapped object of interest discrete curve using a second mapping operator configured according to a second set of terms;

determine a target discrete curve from the target data set, wherein the target discrete curve corresponds to a respective object in the target data set;

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

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

generate pattern matching results based on the distances.

28. The system of claim 27, wherein, in said determining the target discrete curve from the target data set, the program instructions are further executable by the processor to:

determine an initial target discrete curve from the target data set;

map the initial target discrete curve to a first mapped target discrete curve using the first mapping operator; and

map the initial target discrete curve to a second mapped target discrete curve using the second mapping operator;

wherein, in performing curve matching on the first mapped object of interest discrete curve and the target discrete curve, the program instructions are further executable by the processor to;

perform curve matching on the first mapped object of interest discrete curve and the first mapped target discrete curve; and

wherein, in performing curve matching on the second mapped object of interest discrete curve and the target discrete curve, the program instructions are further executable by the processor to;

perform curve matching on the second mapped object of interest discrete curve and the second mapped target discrete curve.

29. A system for matching discrete curves, 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 a target image; and

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

determine an object of interest discrete curve from a template image containing an object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

map the object of interest discrete curve to a first mapped object of interest discrete curve using a first mapping operator;

map the object of interest discrete curve to a second mapped object of interest discrete curve using a second mapping operator;

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

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

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

generate pattern matching results based on the distances.

30. The system of claim 29,

wherein the first mapping operator is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a first class of one or more objects that are not of interest;

wherein the second mapping operator is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a second class of one or more objects that are not of interest.

31. The system of claim 30, wherein the program instructions are further executable by the processor to:

receive one or more images containing the one or more objects of the first class that are not of interest;

determine the first mapping operator based on the template image and the one or more images containing the one or more objects of the first class that are not of interest;

receive one or more images containing the one or more objects of the second class that are not of interest; and

determine the first mapping operator based on the template image and the one or more images containing the one or more objects of the second class that are not of interest.

32. A method for determining the presence of an object of interest in a target data set, the method comprising:

determining an object of interest discrete curve from information regarding the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

mapping the object of interest discrete curve to a first mapped object of interest discrete curve using a mapping operator configured according to a first parameter; and

mapping the object of interest discrete curve to a second mapped object of interest discrete curve using a mapping operator configured according to a second parameter.

acquiring the target data set;

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

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

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

generating pattern matching results based on the distances.

33. The method of claim 32, wherein said determining the target discrete curve from the target data set comprises:

determining an initial target discrete curve from the target data set;

mapping the initial target discrete curve to a first mapped target discrete curve using the mapping operator configured according to a first parameter;

mapping the initial target discrete curve to a second mapped target discrete curve using the mapping operator configured according to a second parameter;

wherein said performing curve matching on the first mapped object of interest discrete curve and the target discrete curve comprises;

performing curve matching on the first mapped object of interest discrete curve and the first mapped target discrete curve; and

wherein said performing curve matching on the second mapped object of interest discrete curve and the target discrete curve comprises;

performing curve matching on the second mapped object of interest discrete curve and the second mapped target discrete curve.

34. The method of claim 32, wherein generating pattern matching results based on the distances comprises:

analyzing said distance for the target discrete curve relative to the first mapped object of interest discrete curve and said distance for the target discrete curve relative to the second mapped object of interest discrete curve; and

determining if said distances indicate a match between the object of interest and the respective object in the target data set in response to said analysis.

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

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

mapping the object of interest discrete curve to a first mapped object of interest discrete curve using a mapping operator configured according to a first parameter; and

mapping the object of interest discrete curve to a second mapped object of interest discrete curve using a mapping operator configured according to a second parameter.

acquiring the target image;

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

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

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

generating pattern matching results based on the distances.

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

means for determining an object of interest discrete curve from information regarding the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

means for mapping the object of interest discrete curve to a first mapped object of interest discrete curve using a first mapping operator configured according to a first set of terms, wherein the first set of terms is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a first class of one or more objects that are not of interest;

means for mapping the object of interest discrete curve to a second mapped object of interest discrete curve using a second mapping operator configured according to a second set of terms, wherein the second set of terms is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a second class of one or more objects that are not of interest;

means for acquiring the target data set;

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

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

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

means for generating pattern matching results based on the distances.

37. The system of claim 36,

wherein said means for determining the target discrete curve from the target data set comprises:

means for determining an initial target discrete curve from the target data set;

means for mapping the initial target discrete curve to a first mapped target discrete curve using the first mapping operator; and

means for mapping the initial target discrete curve to a second mapped target discrete curve using the second mapping operator;

wherein said means for performing curve matching on the first mapped object of interest discrete curve and the target discrete curve comprises;

means for performing curve matching on the first mapped object of interest discrete curve and the first mapped target discrete curve; and

wherein said means for performing curve matching on the second mapped object of interest discrete curve and the target discrete curve comprises;

means for performing curve matching on the second mapped object of interest discrete curve and the second mapped target discrete curve.

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

means for determining an object of interest discrete curve from a template image containing the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

means for mapping the object of interest discrete curve to a first mapped object of interest discrete curve using a first mapping operator configured according to a first set of terms, wherein the first set of terms is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a first class of one or more objects that are not of interest;

means for mapping the object of interest discrete curve to a second mapped object of interest discrete curve using a second mapping operator configured according to a second set of terms, wherein the second set of terms is operable to enhance a distance between mapped discrete curves corresponding to the object of interest and mapped discrete curves corresponding to a second class of one or more objects that are not of interest;

means for acquiring the target image;

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

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

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

means for generating pattern matching results based on the distances.

39. The system of claim 38,

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

means for determining an initial target discrete curve from the target image;

means for mapping the initial target discrete curve to a first mapped target discrete curve using the first mapping operator; and

means for mapping the initial target discrete curve to a second mapped target discrete curve using the second mapping operator;

wherein said means for performing curve matching on the first mapped object of interest discrete curve and the target discrete curve comprises;

means for performing curve matching on the first mapped object of interest discrete curve and the first mapped target discrete curve; and

wherein said means for performing curve matching on the second mapped object of interest discrete curve and the target discrete curve comprises;

means for performing curve matching on the second mapped object of interest discrete curve and the second mapped target discrete curve.

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

determining an object of interest discrete curve from information regarding the object of interest, wherein the object of interest discrete curve corresponds to the object of interest;

mapping the object of interest discrete curve to a plurality of mapped object of interest discrete curves using a respective plurality of mapping operators, wherein the respective mapping operators are each operable to enhance respective distances between discrete curves corresponding to the object of interest and mapped discrete curves corresponding to respective classes of one or more objects that are not of interest;

acquiring the target data set;

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

performing curve matching between the target discrete curve and each of the plurality of mapped object of interest discrete curves, wherein said performing curve matching computes a distance for the target discrete curve relative to each of the plurality of object of interest discrete curves; and

generating pattern matching results based on the distances.

41. The method of claim 40, further comprising:

determining a plurality of background object discrete curves corresponding to respective classes of objects that are not of interest; and

computing the plurality of mapping operators respectively from the object of interest discrete curve and each of the one or more background object discrete curves;

wherein each of the mapping operators operates to amplify differences between the object of interest discrete curve and each of the background object discrete curves.

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

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

mapping the object of interest discrete curve to a plurality of mapped object of interest discrete curves using a respective plurality of mapping operators, wherein the respective mapping operators are each operable to enhance respective distances between discrete curves corresponding to the object of interest and mapped discrete curves corresponding to respective classes of one or more objects that are not of interest;

acquiring the target image;

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

performing curve matching between the target discrete curve and each of the plurality of mapped object of interest discrete curves, wherein said performing curve matching computes a distance for the target discrete curve relative to each of the plurality of object of interest discrete curves; and

generating pattern matching results based on the distances.

43. The method of claim 42, further comprising:

determining a plurality of background object discrete curves corresponding to respective classes of objects that are not of interest; and

computing the plurality of mapping operators respectively from the object of interest discrete curve and each of the one or more background object discrete curves;

wherein each of the mapping operators operates to amplify respective differences between the object of interest discrete curve and each of the background object discrete curves.

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

receiving a first data set, wherein the first data set includes the object of interest;

determining a template discrete curve from the first data set, wherein the template discrete curve corresponds to the object of interest;

receiving a second data set, wherein the second data set includes one or more objects not of interest;

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

computing a plurality of respective mapping operators based on the template discrete curves and each of the one or more background object discrete curves; and

mapping the template discrete curve to one or more mapped template discrete curves using the plurality of respective mapping operators;

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

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

receiving a first image, wherein the first image includes the object of interest;

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

receiving a second image, wherein the second image includes one or more objects not of interest;

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

computing a plurality of respective mapping operators based on the template discrete curves and each of the one or more background object discrete curves; and

mapping the template discrete curve to one or more mapped template discrete curves using the plurality of respective mapping operators;

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