Scoring items

• US 7,978,882 B1
• Filed: 05/21/2010
• Issued: 07/12/2011
• Est. Priority Date: 01/13/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Rowley, Henry A., Malpani, Radhika, Rosenberg, Charles
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US12/785,021
• Time in Patent Office: 417 Days
• Field of Search: 382/100, 382/112, 382135-140, 382155-161, 382/168, 382/181, 382/190, 382/194, 382/199, 382/209, 382/224, 382/232, 382/254, 382/264, 382/275, 382/276, 382/305, 382/310, 382/312, 707/6, 709/224
• US Class Current: 382/112
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition

Abstract

A system identifies an image and determines whether the image contains inappropriate content based on first data associated with the image, second data associated with a document that contains the image or refers to the image, and/or third data associated with a group of documents with which the image is associated.

Claims

1. A method performed by one or more server devices, the method comprising:

extracting, by the one or more server devices, a visual feature from an image that is associated with a web site, where the extracted visual feature of the image includes a color;

determining, by the one or more server devices, a score for the image, the score representing a likelihood that the image includes inappropriate content, where the score is based on;

the extracted visual feature of the image, and

one or more other scores, associated with a distribution of the extracted visual feature across one or more other images associated with the web site;

associating, by the one or more server devices, the determined score with the image;

associating a tag with the image, based on the score; and

using, by the one or more server devices, the tag to determine whether to provide the image to a user.

2. The method of claim 1, where the image is associated with a first document of the web site, and where the one or more other images are associated with one or more other documents of the web site.

3. The method of claim 1, where the determining the score includes:

representing the web site using one or more sets of statistics, and

using the one or more sets of statistics in determining the score for the image.

4. The method of claim 1, where the determining the score includes:

analyzing text in a document that includes the image,

determining a text score for the document based on the analyzing, the text score representing a likelihood that the document contains inappropriate content, and

using the text score in determining the score for the image.

5. The method of claim 4, where the determining the score further includes:

generating a set of text-based statistics for one or more other documents, that include the one or more other images, based on the text score, and

using the set of text-based statistics in determining the score for the image.

6. The method of claim 1, where the determining the score further includes:

generating a set of image-based statistics for the extracted visual feature based on the one or more other images, and

using the set of image-based statistics in determining the score for the image.

7. The method of claim 6, where the determining the score further includes:

generating a set of image-based statistics for one or more documents, that include the one or more other images, based on image scores of the one or more other images, and

using the set of image-based statistics, for the one or more other documents, in determining the score for the image.

8. The method of claim 1, further comprising:

extracting a plurality of visual features from the image,

where the determining the score for the image includes;

using the plurality of extracted visual features from the image to determine the score for the image.

9. The method of claim 1, where the color is associated with a skin tone.

10. A method performed by one or more server devices, the method comprising:

extracting, by the one or more server devices, a visual feature from an image, where the visual feature includes a color;

generating, by the one or more server devices, a first score for the image based on the extracted visual feature;

generating, by the one or more server devices, a first set of statistics for the extracted visual feature representing a distribution of the feature across other images on one or more documents with which the image is associated;

generating a second set of statistics based on the first score, the second set of statistics representing a distribution of the first score across the other images on the one or more documents;

generating, by the one or more server devices, a second score for the image based on;

the first score,

the first set of statistics, and

the second set of statistics; and

using, by the one or more server devices, the second score to determine whether to provide the image to a user.

11. The method of claim 10, further comprising:

determining that the user has selected an option not to receive the image when the score for the image is above a threshold.

12. The method of claim 11, further comprising:

providing the option to the user, where the option includes a plurality of levels of screening, where the level of screening indicates the threshold.

13. The method of claim 12, where the plurality of levels include at least one of low, moderate, and high.

14. A system, comprising:

a memory to store instructions; and

one or more processors to execute the instructions, to;

extract a visual feature from an image that is associated with a web site, where the extracted visual feature of the image includes a color,

determine a score for the image, the score representing a likelihood that the image includes inappropriate content, where the score is based on;

the extracted visual feature of the image, and

one or more other scores, associated with a distribution of the extracted visual feature across one or more other images associated with the web site;

associate the determined score with the image;

associate a tag with the image, based on the score; and

use the associated tag to determine whether to provide the image to a user.

15. The system of claim 14, where the image is presented via a first document of the web site, and where the one or more other images are associated with one or more other documents of the web site.

16. The system of claim 14, where when determining the score, the one or more processors are to:

analyze text in a document that includes the image,

determine a text score for the document based on the analyzing, the text score representing a likelihood that the document contains inappropriate content, and

use the text score in determining the score for the image.

17. A computer-readable storage medium having computer-readable instructions stored thereon, the computer-readable instructions comprising:

one or more instructions to extract a visual feature from an image that is associated with a web site, where the extracted visual feature of the image includes a color;

one or more instructions to determine a score for the image, the score representing a likelihood that the image includes inappropriate content, where the score is based on;

the extracted visual feature of the image, and

one or more other scores, associated with a distribution of the extracted visual feature across one or more other images associated with the web site;

one or more instructions to associate the determined score with the image;

one or more instructions to associate a tag with the image, based on the score; and

one or more instructions to use the tag to determine whether to provide the image to a user.

18. The computer-readable storage medium of claim 17, where the image is associated with a first document of the web site, and where the one or more other images are associated with one or more other documents of the web site.

19. The computer-readable storage medium of claim 17, where the one or more instructions to determine the score include:

one or more instructions to represent the web site using one or more sets of statistics, and

one or more instructions to use the one or more sets of statistics in determining the score for the image.

20. The computer-readable storage medium of claim 17, where the one or more instructions to determine the score include:

one or more instructions to analyze text in a document that includes the image,

one or more instructions to determine a text score for the document based on the analyzing, the text score representing a likelihood that the document contains inappropriate content, and

one or more instructions to use the text score in determining the score for the image.

21. The computer-readable storage medium of claim 20, where the one or more instructions to determine the score further include:

one or more instructions to generate a set of text-based statistics for one or more other documents, that include the one or more other images, based on the text score, and

one or more instructions to use the set of text-based statistics in determining the score for the image.

22. The computer-readable storage medium of claim 17, where the one or more instructions to determine the score further include:

one or more instructions to generate a set of image-based statistics for the extracted visual feature based on the one or more other images, and

one or more instructions to use the set of image-based statistics in determining the score for the image.

23. The computer-readable storage medium of claim 22, where the one or more instructions to determine the score further include:

one or more instructions to generate a set of image-based statistics for one or more documents, that include the one or more other images, based on image scores of the one or more other images, and

one or more instructions to use the set of image-based statistics, for the one or more other documents, in determining the score for the image.

24. The computer-readable storage medium of claim 17, the computer-readable instructions further comprising:

one or more instructions to extract a plurality of visual features from the image, where the plurality of visual features includes the visual feature,

where the one or more instructions to determine the score for the image include;

one or more instructions to use the plurality of extracted visual features from the image to determine the score for the image.

25. The computer-readable storage medium of claim 17, where the color is associated with a skin tone.