Image processing and identification system, method and apparatus

• US 7,555,487 B2
• Filed: 08/19/2005
• Issued: 06/30/2009
• Est. Priority Date: 08/20/2004
• Status: Active Grant

• Current Assignee: XWEB Incorporated
• Original Assignee: XWEB Incorporated
• Inventors: Levi, Ronald M., Shprung, Shai
• Primary Examiner(s): Vo; Tim T.
• Assistant Examiner(s): Morrison; Jay A
• Application Number:
  US11/207,636
• Publication Number:
  US 20060059116A1
• Time in Patent Office: 1,411 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Embodiments of the present invention are directed to a system and method for processing and identifying a first data file, the first data file having set of data points, wherein each data point is defined by an x,y coordinate and has a value corresponding to the lightness or darkness of the data resident at the data point, comprising: dividing the first data file into segments; identifying the coordinates of at least one contrast point for each segment; creating a first set of identifiers for the data file, creating a second set of identifiers for a second data file, comparing at least one identifier of the first data file to the corresponding identifier in the second data file; and assessing whether at least a portion of the second data file matches at least a portion of the first data file.

Claims

1. A method for determining whether first and second data files match, the first and second data files each having a set of data points, wherein each data point is defined by an x,y coordinate and has a characteristic corresponding to the data resident at the data point, comprising:

dividing the first data file that is stored on a data store into plural segments;

selecting at least one data point in each of the plural segments based on a predefined characteristic of the data point;

identifying the coordinates of the at least one selected data point in each segment;

creating a first set of identifiers for the first data file wherein the first set of identifiers includes a respective identifier for each respective segment and that is at least partially determined from the x,y coordinate of at least one selected data point in its associated segment;

associating a respective importance value with each respective segment, the importance value associated with at least one of the segments differing from the importance value associated with at least one other one of the segments;

identifying a second data file;

creating a second set of identifiers for the second data file, the second set of identifiers includes a respective second identifier corresponding to each respective identifier in the first set of identifiers by being at least partially determined from the x,y coordinates of a data point in the second data file that has a characteristic corresponding to the predefined characteristic;

comparing at least one identifier in the first set of identifiers to the corresponding identifier in the second set of identifiers; and

assessing whether at least a portion of the second data file matches at least a portion of the first data file, based at least partially on results of the comparing and the importance value associated with each segment for which said at least one identifier in the first set is created.

2. A method as claimed in claim 1, wherein creating a second set of identifiers for the second data file comprises:

dividing the second data file into segments;

selecting at least one data point in each of the plural segments of the second data file based on a characteristic of the data point corresponding to the predefined characteristic for which at least one of the first set of identifiers is selected; and

identifying the x,y coordinates of the at least one selected data point for each segment for the second data file.

3. A method as claimed in claim 1, wherein assessing whether at least a portion of the second data files matches at least a portion of the first data file, comprises:

calculating the difference of at least one identifier in the first set of identifiers and the corresponding identifier in the second set of identifiers, wherein the selected identifier is associated with a particular segment; and

assigning a scoring value for the segment based at least partially upon the calculated difference and the importance value associated with the segment.

4. A method as claimed in claim 1, wherein creating a first set of identifiers comprises creating a further identifier for the first set of identifiers by:

selecting a subset of segments for the first data file, each selected segment having a number of pixels of a first color and a number of pixels of a second color;

calculating the difference between the number of the pixels of the first color in the selected subset of segments and the number of pixels of the second color in the selected subset of segments.

5. A method as claimed in claim 1, wherein creating a first set of identifiers comprises creating at least one further identifier for the first set of identifiers by:

summing the values of each x coordinate for the selected data points and storing a value that is at least partially defined by that summation in a database; and

summing the values of each y coordinate for the selected data points and storing a value that is at least partially defined by that summation in a database.

6. A method as claimed in claim 4, wherein creating a second set of identifiers comprises creating a further identifier for the second set of identifiers by:

dividing the second data file into segments;

selecting a subset of segments for the second data file, each selected segment having a number of pixels of a first color and a number of pixels of a second color; and

calculating the difference of the number of pixels of the first color and pixels of the second color in the selected subset of segments;

wherein comparing at least one identifier in the first set of identifiers to the corresponding identifier in the second set of identifiers further comprises comparing he calculated difference of the number of pixels of the first and second colors in the subset of segments selected from the first data file with the difference in the number of pixels of the first and second colors in the subset of segments selected from the second data file.

7. A method as claimed in claim 1, further comprising:

calculating a brightness value for the first data file, wherein the brightness value is the difference between the total number of bright pixels and the total number of dark pixels for a selected subset of segments;

calculating a brightness value for the second data file, wherein the brightness value is the difference between the total number of bright pixels and the total number of dark pixels for the selected subset of segments; and

comparing the brightness value of the first data file and the brightness value of the second data file.

8. A method as claimed in claim 7, further comprising:

selecting the second data file for visual review if the brightness value for the first data file substantially matches the brightness value for the second data file; and

eliminating the second data file as a false positive if the difference between the brightness value for the first data file and the brightness value for the second data file exceeds a predefined tolerance.

9. A method as claimed in claim 8, further comprising:

transmitting notification that the second file is an unauthorized use of the first data file, if the brightness values are within the predefined tolerance.

10. A method as claimed in claim 1, wherein selecting at least one data point comprises selecting a contrast point by;

selecting a segment from the plural segments;

selecting a first data point in the selected segment as the currently identified contrast point and storing a brightness value of the first data point;

comparing the brightness value of the currently identified contrast point to the brightness value of other data points in the segment until the brightness value of one of the other data points in the segment differs from the brightness value of the currently identified contrast point by a predefined amount;

identifying the data point having a brightness value differing from the brightness value of the currently identified contrast point as the new currently identified contrast point; and

repeating the steps of comparing the brightness value and identifying the data point having a brightness value differing from the brightness value of the currently identified contrast point as the new currently identified contrast point until all of the remaining data points in the segment have been compared.

11. A method as claimed in claim 1, wherein the first data and second data file have an original orientation, the method further comprising comparing the original orientation of the first data file and the second data file.

12. A method as claimed in claim 10, wherein the value of the data point is calculated by summing the brightness values of the selected data point and data points proximally located to the selected data point and dividing the summation by a predefined integer, wherein the integer is less than the number of data points used in the summation.

13. A method as claimed in claim 1, wherein selecting at least one data point in each of the plural segments based on a predefined characteristic of the data point comprises selecting at least one data point in each of the plural segments based on the brightness of the data resident at the data point.

14. A method as claimed in claim 1, wherein selecting at least one data point in each of the plural segments based on a predefined characteristic of the data point comprises selecting at least one data point in each of the plural segments having a brightness value that results in a visible contrast relative to other portions of the segment from which the data point is selected.

15. A method as claimed in claim 1, wherein selecting at least one data point in each of the plural segments based on a predefined characteristic of the data point comprises selecting at least one contrast data point in each of the plural segments having a brightness value that results in a visible brighter portion relative to other portions of the segment from which the data point is selected.

16. A method as claimed in claim 1, wherein selecting at least one data point in each of the plural segments based on a predefined characteristic of the data point comprises selecting at least one contrast data point in each of the plural segments having a brightness value that results in a visible darker portion relative to other portions of the segment from which the data point is selected.

17. A method as claimed in claim 1, wherein each of the first and second data files comprises a data file for a fixed image and each selected data point comprises a data point in a fixed image.

18. A method as claimed in claim 1, wherein each of the first and second data files comprises a data file for a photograph image and each selected data point comprises a data point in a photograph image.

19. A method as claimed in claim 2, wherein each identifier in the second set of identifiers is at least partially determined from the x,y coordinate of the at least one selected data point in an associated segment.

20. A method as claimed in claim 2, wherein each identifier that is associated with a respective segment of one of the first and second data files is at least partially determined from the summation of the x and y coordinates of at least one selected data point in its associated segment.

21. A method as claimed in claim 4, wherein the pixels of the first color are red pixels and the pixels of the second color are blue pixels.

22. A method as claimed in claim 6, wherein the pixels of the first color are red pixels and the pixels of the second color are blue pixels.

23. A method as claimed in claim 10, wherein the value of the data point is calculated by summing the brightness values of the selected data point and data points proximally located to the selected data point and dividing the summation by the number of data points included in the summation or a predefined integer.

24. A method as claimed in claim 1, wherein;

the data points of each of the first and second data files correspond to data points of an image, the image having an horizontal dimension and a vertical dimension when viewed in a normal orientation, the image extending a number of data points in the horizontal dimension and a number of data points in the vertical dimension, and

creating a first set of identifiers comprises creating a further first identifier in the first set of identifiers for indicating an horizontal orientation in the event that the total number of data points extending in the horizontal dimension of the image corresponding to the first data file is greater than the total number of data points extending in the vertical dimension of that image, and for indicating a vertical orientation in the event that the total number of data points extending in the vertical dimension of the image corresponding to the first data file is greater than the total number of data points extending in the horizontal dimension of that image;

creating a second set of identifiers comprises creating a further second identifier in the second set of identifiers for indicating an horizontal orientation in the event that the total number of data points extending in the horizontal dimension of the image corresponding to the second data file is greater than the total number of data points extending in the vertical dimension of that image, and for indicating a vertical orientation in the event that the total number of data points extending in the vertical dimension of the image corresponding to the second data file is greater than the total number of data points extending in the horizontal dimension of that image; and

comparing comprises comparing the further first identifier with the further second identifier.