Method and mechanism for processing image data

• US 7,627,166 B2
• Filed: 11/30/2005
• Issued: 12/01/2009
• Est. Priority Date: 09/28/2005
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Shah, Shesha
• Primary Examiner(s): Ahmed; Samir A.
• Assistant Examiner(s): BEKELE, MEKONEN T
• Application Number:
  US11/291,183
• Publication Number:
  US 20070076950A1
• Time in Patent Office: 1,462 Days
• Field of Search: 382/162, 382/165, 382/167, 382/170, 250/587
• US Class Current: 382/162
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A method and apparatus for processing image data is provided. Color image data is processed to generate gray scale image data, which may comprise a set of data values. Each data value, of the set of data values, may identify a gray scale value.

A frequency distribution that indicates a frequency of occurrence of each gray scale value identified by the set of data values is determined. The uniformity of the frequency distribution is determined. A determination of how close the frequency determination corresponds to a predetermined distribution is made. The color image data is classified as a particular type of image data based on (a) whether the frequency determination corresponds to the predetermined distribution by a first threshold, and (b) whether the uniformity of the frequency distribution exceeds a second threshold.

Claims

1. A method for processing image data, comprising:

processing color image data to generate gray scale image data, wherein the gray scale image data comprises a set of data values, wherein each data value of the set of data values identifies a gray scale value of a sequence of gray scale values;

determining a first measure, wherein the first measure is a frequency distribution that indicates a frequency of occurrence of each gray scale value, of the sequence of gray scale values, identified by the set of data values;

determining a second measure that indicates the uniformity of the first measure;

determining a third measure that indicates how close the first measure corresponds to a second frequency distribution; and

upon determining that the third measure exceeds a first threshold and the second measure exceeds a second threshold, classifying the color image data as a first type of image data;

wherein the image data is processed by one or more processors.

2. The method of claim 1, further comprising:

upon determining that either the third measure does not exceed the first threshold or the second measure does not exceed the second threshold, classifying the color image data as a second type of image data.

3. The method of claim 2, further comprising:

in response to classifying the color image data as the second type of image data, then determining the color image data does not correspond to an image of a face or of offensive content.

4. The method of claim 1, further comprising:

generating a normalized first measure that represents a normalized luminance histogram of the gray scale image data.

5. The method of claim 1, wherein the second measure is performed by calculating an entropy value.

6. The method of claim 1, wherein the step of determining the third measure comprises:

determining a chi-squared test of the first measure against the second frequency distribution.

7. The method of claim 1, wherein the second frequency distribution is a laplacian distribution.

8. The method of claim 1, wherein the first threshold represents at least an about 80% correspondence between the first measure and the second frequency distribution.

9. The method of claim 1, wherein the color image data corresponds to a thumbnail image.

10. The method of claim 1, in response to determining that a particular image is classified as a graphic, then determining the image does not display a face or offensive content.

11. The method of claim 1, further comprising:

receiving a request for one or more sets of image data, wherein the color image data is in the one or more sets of image data; and

processing the request based, at least in part, on the classification of the color image data.

12. The method of claim 11, wherein the request is submitted using a web page, and wherein the step of processing the request comprises identifying the one or more sets of image data that matches a set of characteristics identified by said request.

13. A machine-readable medium carrying one or more sequences of instructions for processing image data, wherein execution of the one or more sequences of instructions by one or more processors causes the one or more processors to perform the steps of:

processing color image data to generate gray scale image data, wherein the gray scale data comprises a set of data values, wherein each data value of the set of data values identifies a gray scale value of a sequence of gray scale values;

determining a first measure, wherein the first measure is a frequency distribution that indicates a frequency of occurrence of each gray scale value, of the sequence of gray scale values, identified by the set of data values;

determining a second measure that indicates the uniformity of the first measure;

determining a third measure that indicates how close the first measure corresponds to a second frequency distribution; and

upon determining that the third measure exceeds a first threshold and the second measure exceeds a second threshold, classifying the color image data as a first type of image data.

14. The machine-readable medium of claim 13, wherein execution of the one or more sequences of instructions by the one or more processors further causes the one or more processors to perform the step of:

upon determining that either the third measure does not exceed the first threshold or the second measure does not exceed the second threshold, classifying the color image data as a second type of image data.

15. The machine-readable medium of claim 14, wherein execution of the one or more sequences of instructions by the one or more processors further causes the one or more processors to perform the step of:

in response to classifying the color image data as the second type of image data, then determining the color image data does not correspond to an image of a face or of offensive content.

16. The machine-readable medium of claim 13, wherein execution of the one or more sequences of instructions by the one or more processors further causes the one or more processors to perform the step of:

generating a normalized first measure that represents a normalized luminance histogram of the gray scale image data.

17. The machine-readable medium of claim 13, wherein the second measure is performed by calculating an entropy value.

18. The machine-readable medium of claim 13, wherein the step of determining the third measure comprises:

determining a chi-squared test of the first measure against the second frequency distribution.

19. The machine-readable medium of claim 13, wherein the second frequency distribution is a laplacian distribution.

20. The machine-readable medium of claim 13, wherein the first threshold represents at least an about 80% correspondence between the first measure and the second frequency distribution.

21. The machine-readable medium of claim 13, wherein the color image data corresponds to a thumbnail image.

22. The machine-readable medium of claim 13, in response to determining that a particular image is classified as a graphic, then determining the image does not display a face or offensive content.

23. The machine-readable medium of claim 13, wherein execution of the one or more sequences of instructions by the one or more processors further causes the one or more processors to perform the steps of:

receiving a request for one or more sets of image data, wherein the color image data is in the one or more sets of image data; and

processing the request based, at least in part, on the classification of the color image data.

24. The machine-readable medium of claim 23, wherein the request is submitted using a web page, and wherein the step of processing the request comprises identifying the one or more sets of image data that matches a set of characteristics identified by said request.

25. An apparatus for processing image data, comprising:

one or more processors;

a machine-readable medium carrying one or more sequences of instructions, wherein execution of the one or more sequences of instructions by the one or more processors causes the one or more processors to perform the steps of;

processing color image data to generate gray scale image data, wherein the gray scale image data comprises a set of data values, wherein each data value of the set of data values identifies a gray scale value of a sequence of gray scale values;

determining a first measure, wherein the first measure is a frequency distribution that indicates a frequency of occurrence of each gray scale value, of the sequence of gray scale values, identified by the set of data values;

determining a second measure that indicates the uniformity of the first measure;

determining a third measure that indicates how close the first measure corresponds to a second frequency distribution; and

upon determining that the third measure exceeds a first threshold and the second measure exceeds a second threshold, classifying the color image data as a first type of image data.

26. The apparatus of claim 25, wherein execution of the one or more sequences of instructions by the one or more processors causes the one or more processors to perform the step of:

upon determining that either the third measure does not exceed the first threshold or the second measure does not exceed the second threshold, classifying the color image data as a second type of image data.

27. The apparatus of claim 26, wherein execution of the one or more sequences of instructions by the one or more processors causes the one or more processors to perform the step of:

in response to classifying the color image data as the second type of image data, then determining the color image data does not correspond to an image of a face or of offensive content.

28. The apparatus of claim 25, wherein execution of the one or more sequences of instructions by the one or more processors causes the one or more processors to perform the step of:

generating a normalized first measure that represents a normalized luminance histogram of the gray scale image data.

29. The apparatus of claim 25, wherein the second measure is performed by calculating an entropy value.

30. The apparatus of claim 25, wherein the step of determining the third measure comprises:

determining a chi-squared test of the first measure against the second frequency distribution.

31. The apparatus of claim 25, wherein the second frequency distribution is a laplacian distribution.

32. The apparatus of claim 25, wherein the first threshold represents at least an about 80% correspondence between the first measure and the second frequency distribution.

33. The apparatus of claim 25, wherein the color image data corresponds to a thumbnail image.

34. The apparatus of claim 25, in response to determining that a particular image is classified as a graphic, then determining the image does not display a face or offensive content.

35. The apparatus of claim 25, wherein execution of the one or more sequences of instructions by the one or more processors causes the one or more processors to perform the steps of:

receiving a request for one or more sets of image data, wherein the color image data is in the one or more sets of image data; and

processing the request based, at least in part, on the classification of the color image data.

36. The apparatus of claim 35, wherein the request is submitted using a web page, and wherein the step of processing the request comprises identifying the one or more sets of image data that matches a set of characteristics identified by said request.