Systems and methods for obtaining templates for tessellated images

1. A method for selecting a template image for a tessellated image, the method comprising:

analyzing the tessellated image using a sample area image from the tessellated image to determine a template unit size for the template image;

defining pixel analysis line segments configured for identifying template unit boundaries of the template image based at least in part on the template unit size; and

selecting the template image based at least in part on the template unit boundaries identified using the pixel analysis line segments.

2. The method of claim 1 , wherein the template unit size and the template unit boundaries correspond to a pattern unit of the tessellated image.

3. The method of claim 1 , wherein the analyzing the tessellated image using the sample area image from the tessellated image to determine the template unit size comprises:

performing convolution processing with respect to the sample area image and the tessellated image;

identifying one or more peaks corresponding to locations of putative pattern units of the tessellated image from results of the convolution processing; and

determining the template unit size based on a spacing of the one or more peaks.

4. The method of claim 3 , wherein the identifying the one or more peaks corresponding to locations of the putative pattern units comprises:

analyzing the results of the convolution processing to identify local maximum peaks.

5. The method of claim 3 , wherein the determining the template unit size based on the spacing of the one or more peaks comprises:

performing vector statistical analysis with respect to peak intervals of the one or more peaks corresponding to locations of the putative pattern units in horizontal and vertical directions to obtain the template unit size.

6. The method of claim 3 , further comprising:

evaluating an orientation of the one or more peaks corresponding to locations of the putative pattern units to determine if the one or more peaks corresponding to locations of the putative pattern units are oriented in a geometric normal position.

7. The method of claim 3 , further comprising:

determining if a number of the one or more peaks corresponding to locations of the putative pattern units meets a predetermined threshold number; and

if the number of the one or more peaks does meet the predetermined threshold number, proceeding to determine the template unit size; or

if the number of the one or more peaks does not meet the predetermined threshold number, selecting a different sized sample area image from the tessellated image and repeating the analyzing the tessellated image to determine a template unit size for the template image using the different sized sample area image.

8. The method of claim 7 , wherein the different sized sample area image is of a size smaller than that of the sample area image.

9. The method of claim 1 , further comprising:

analyzing pixels of the tessellated image corresponding to positions of a plurality of pixel analysis line segments of the pixel analysis line segments over the tessellated image; and

identifying individual template unit boundaries of the template image based upon the analyzing indicating pixels of the tessellated image corresponding to a position of ones of the plurality of pixel analysis line segments meeting predetermined criteria.

10. The method of claim 9 , wherein the identifying individual template unit boundaries of the template image based upon the analyzing indicating pixels of the tessellated image corresponding to a position of ones of the plurality of pixel analysis line segments meeting predetermined criteria comprises:

determining that data of histograms of the pixels of the tessellated image corresponding to a position of a plurality of pixel analysis line segments have a same attribute.

11. The method of claim 9 , wherein the plurality of pixel analysis line segments are configured based at least in part on the template unit size.

12. The method of claim 11 , wherein the plurality of pixel analysis line segments comprise a plurality of horizontal pixel analysis line segments spaced apart vertically a height of the template unit size.

13. The method of claim 12 , wherein the plurality of horizontal pixel analysis line segments have lengths greater than a width of the template unit size.

14. The method of claim 11 , wherein the plurality of pixel analysis line segments comprise a plurality of vertical pixel analysis line segments spaced apart horizontally a width of the template unit size.

15. The method of claim 14 , wherein the plurality of vertical pixel analysis line segments have lengths greater than a height of the template unit size.

16. The method of claim 9 , further comprising:

sliding the plurality of pixel analysis line segments over the tessellated image, wherein the positions of the plurality of pixel analysis line segments analyzed for meeting the predetermined criteria to identify the individual template unit boundaries comprise sliding positions of the plurality of pixel analysis line segments.

17. The method of claim 1 , further comprising:

using the template image to locate individual pattern units within the tessellated image.

18. The method of claim 17 , further comprising:

computing a template matching score with respect to a match of the template image to an instance of a pattern unit within the tessellated image;

determining if the template matching score meets a predetermined threshold score; and

if the template matching score does not meet the predetermined threshold score, dynamically updating the template image.

19. The method of claim 18 , wherein the dynamically updating the template image comprises:

matching feature points of the instance of the pattern unit with feature points of the template image; and

transforming the template image to more closely match the instance of the pattern unit.

20. A method for selecting a template image for a tessellated image, the method comprising:

analyzing the tessellated image using a sample area image from the tessellated image to determine a template unit size for the template image;

defining a plurality of pixel analysis line segments configured for identifying template unit boundaries of the template image based upon the template unit size;

sliding the plurality of pixel analysis line segments over the tessellated image;

analyzing pixels of the tessellated image corresponding to positions of a plurality of pixel analysis line segments of the pixel analysis line segments as slid over the tessellated image;

identifying individual template unit boundaries of the template image based upon the analyzing indicating pixels of the tessellated image corresponding to a position of ones of the plurality of pixel analysis line segments meeting predetermined criteria; and

selecting the template image based at least in part on the individual template unit boundaries identified based upon the analyzing.

21. The method of claim 20 , wherein the analyzing the tessellated image using the sample area image from the tessellated image to determine the template unit size comprises:

performing convolution processing with respect to the sample area image and the tessellated image;

identifying one or more peaks corresponding to locations of putative pattern units of the tessellated image by analyzing the results of the convolution processing to identify local maximum peaks; and

determining the template unit size based on a spacing of the one or more peaks by performing vector statistical analysis with respect to peak intervals of the one or more peaks corresponding to locations of the putative pattern units in horizontal and vertical directions to obtain the template unit size.

22. The method of claim 21 , further comprising:

determining if a number of the one or more peaks corresponding to locations of the putative pattern units meets a predetermined threshold number; and

if the number of the one or more peaks does meet the predetermined threshold number, proceeding to determine the template unit size; or

if the number of the one or more peaks does not meet the predetermined threshold number, selecting a smaller sized sample area image from the tessellated image and repeating the analyzing the tessellated image to determine a template unit size for the template image using the smaller sized sample area image.

23. The method of claim 20 , wherein the identifying individual template unit boundaries of the template image based upon the analyzing indicating pixels of the tessellated image corresponding to a position of ones of the plurality of pixel analysis line segments meeting predetermined criteria comprises:

determining that data of histograms of the pixels of the tessellated image corresponding to a position of a plurality of pixel analysis line segments have a same attribute.

24. The method of claim 20 , wherein the plurality of pixel analysis line segments are configured based at least in part on the template unit size.

25. The method of claim 24 , wherein the plurality of pixel analysis line segments comprise a plurality of horizontal pixel analysis line segments spaced apart vertically a height of the template unit size.

26. The method of claim 25 , wherein the plurality of horizontal pixel analysis line segments have lengths greater than a width of the template unit size.

27. The method of claim 20 , wherein the plurality of pixel analysis line segments comprise a plurality of vertical pixel analysis line segments spaced apart horizontally a width of the template unit size.

28. The method of claim 27 , wherein the plurality of vertical pixel analysis line segments have lengths greater than a height of the template unit size.

29. The method of claim 20 , further comprising:

using the template image to locate individual pattern units within the tessellated image.

30. The method of claim 29 , further comprising:

computing a template matching score with respect to a match of the template image to an instance of a pattern unit within the tessellated image;

determining if the template matching score meets a predetermined threshold score; and

if the template matching score does not meet the predetermined threshold score, dynamically updating the template image.

31. The method of claim 30 , wherein the dynamically updating the template image comprises:

matching feature points of the instance of the pattern unit with feature points of the template image; and

transforming the template image to more closely match the instance of the pattern unit.

32. A system for selecting a template image for a tessellated image, the system comprising:

a memory; and

at least one processor in communication with the memory, wherein the at least one processor is configured to;

analyze the tessellated image using a sample area image from the tessellated image to determine a template unit size for the template image;

define a plurality of pixel analysis line segments configured for identifying template unit boundaries of the template image based upon the template unit size;

slide the plurality of pixel analysis line segments over the tessellated image;

analyze pixels of the tessellated image corresponding to positions of a plurality of pixel analysis line segments of the pixel analysis line segments as slid over the tessellated image;

identify individual template unit boundaries of the template image based upon the analyzing pixels of the tessellated image corresponding to a position of ones of the plurality of pixel analysis line segments meeting predetermined criteria; and

select the template image based at least in part on the individual template unit boundaries identified based upon the analyzing.

33. The system of claim 32 , wherein the at least one processor is further configured to:

perform convolution processing with respect to the sample area image and the tessellated image;

identify one or more peaks corresponding to locations of putative pattern units of the tessellated image by analyzing the results of the convolution processing to identify local maximum peaks; and

determine the template unit size based on a spacing of the one or more peaks by performing vector statistical analysis with respect to peak intervals of the one or more peaks corresponding to locations of the putative pattern units in horizontal and vertical directions to obtain the template unit size.

34. The system of claim 33 , wherein the at least one processor is further configured to:

determine if a number of the one or more peaks corresponding to locations of the putative pattern units meets a predetermined threshold number; and

proceed to determine the template unit size if the number of the one or more peaks does meet the predetermined threshold number; or

select a smaller sized sample area image from the tessellated image and repeating the analyzing the tessellated image to determine a template unit size for the template image using the smaller sized sample area image if the number of the one or more peaks does not meet the predetermined threshold number.

35. The system of claim 32 , wherein the at least one processor is further configured to:

use the template image to locate individual pattern units within the tessellated image;

compute a template matching score with respect to a match of the template image to an instance of a pattern unit within the tessellated image;

determine if the template matching score meets a predetermined threshold score; and

dynamically update the template image if the template matching score does not meet the predetermined threshold score.