Identifying image type in a capture system

• US 8,200,026 B2
• Filed: 05/26/2009
• Issued: 06/12/2012
• Est. Priority Date: 11/21/2005
• Status: Active Grant

• Current Assignee: McAfee, LLC
• Original Assignee: McAfee, Inc. (McAfee, LLC)
• Inventors: Deninger, William, de la Iglesia, Erik
• Primary Examiner(s): DO, ANH HONG
• Application Number:
  US12/472,150
• Publication Number:
  US 20090232391A1
• Time in Patent Office: 1,113 Days
• Field of Search: 382/224, 382/223, 382/195, 382/165, 382/276, 382/128, 382/173, 382/103, 348/172, 348/51, 707/E17.02, 707/999, 358/464, 345/421, 380/201, 455/420, 455/418, 715/788
• US Class Current: 382/224
• CPC Class Codes: G06F 21/55 Detecting local intrusion or implementing counter-measures
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: H04L 63/123 received data contents, e.g. message integrity

Abstract

Visual objects can be classified according to image type. In one embodiment, the present invention includes capturing a visual object, and decompressing the visual object to a colorspace representation exposing each pixel. The contribution of each pixel to a plurality of image types can then be determined. Then, the contributions can be combined, and the image type of the visual object can be determined based on the contributions.

Claims

1. A method to be executed in an electronic environment in which a processor is used, comprising:

receiving an object sought to be transmitted over a network;

determining a contribution of pixels associated with the object; and

determining an image type of the object based on the contribution of the pixels.

2. The method of claim 1, wherein the determining of the contribution of the pixels comprises mapping a selected pixel to possible values to quantify a contribution of the selected pixel to the image type.

3. The method of claim 2, wherein the mapping of the selected pixel is based on a position of the selected pixel within the object.

4. The method of claim 2, wherein the mapping of the selected pixel comprises mapping the selected pixel to the possible values that indicate no contribution, a weak contribution, or a strong contribution to a particular image type.

5. The method of claim 2, wherein the mapping is different for particular pixels at an edge of the object than for particular pixels in a center area of the object.

6. The method of claim 1, further comprising:

selecting a portion of the object for determining the contribution of the pixels associated with the object.

7. The method of claim 6, wherein the selecting of the portion is based on a size, a shape, or particular dimensions of the object.

8. The method of claim 1, further comprising:

decompressing an object from its native format to a plurality of pixels of a color space.

9. The method of claim 1, further comprising:

classifying the object as related to the image type if a sum of the contributions of the pixels of the image type exceeds a predetermined threshold.

10. The method of claim 9, wherein exceeding the threshold is used to eliminate one of the image types from possible consideration as a correct image type for the object.

11. The method of claim 1, wherein the image type comprises a plurality of image types that include one or more of a skintone image type, an x-ray image type, a grayscale image type, a graph image type, an astrological image type, a geographic image type, a circuit design mask image type, and a banner advertisement image type.

12. The method of claim 1, further comprising:

configuring a policy that outlines one or more image types that are prohibited from being transmitted over the network.

13. The method of claim 1, further comprising:

querying for one or more image types sought to be transmitted over the network.

14. The method of claim 1, further comprising:

providing a tag that identifies the object as being related to a particular image type.

15. The method of claim 14, further comprising:

storing the tag in a database, wherein the tag can be used in processing a query for one or more image types.

16. An apparatus, comprising:

a capture element configured to receive an object sought to be transmitted over a network;

a classification module configured to determine a contribution of pixels associated with the object; and

an image classifier module configured to determine an image type of the object based on the contribution of the pixels.

17. The apparatus of claim 16, further comprising:

a pixel map module configured to map a selected pixel to possible values to quantify a contribution of the selected pixel to the image type.

18. The apparatus of claim 17, wherein the mapping of the selected pixel is based on a position of the selected pixel within the object.

19. The apparatus of claim 17, wherein the mapping of the selected pixel comprises mapping the selected pixel to the possible values that indicate no contribution, a weak contribution, or a strong contribution to a particular image type.

20. The apparatus of claim 17, wherein the mapping is different for particular pixels at an edge of the object than for particular pixels in a center area of the object.

21. The apparatus of claim 16, further comprising:

a scaling module configured to select a portion of the object for determining the contribution of the pixels associated with the object.

22. The apparatus of claim 21, wherein the selecting of the portion is based on a size, a shape, or particular dimensions of the object.

23. The apparatus of claim 16, further comprising:

a decompressing module configured to decompress an object from its native format to a plurality of pixels of a color space.

24. The apparatus of claim 16, further comprising:

a tag generator configured to provide a tag that identifies the object as being related to a particular image type.

25. The apparatus of claim 24, further comprising:

a memory element configured to store the tag, wherein the tag can be used in processing a query for one or more image types.

26. Logic encoded in non-transitory media for execution and when executed by a processor is operable to:

receive an object sought to be transmitted over a network;

determine a contribution of pixels associated with the object; and

determine an image type of the object based on the contribution of the pixels.

27. The logic of claim 26, wherein the determining of the contribution of the pixels comprises mapping a selected pixel to possible values to quantify a contribution of the selected pixel to the image type, wherein the mapping of the selected pixel is based on a position of the selected pixel within the object.

28. The logic of claim 26, wherein the code is further operable to:

select a portion of the object for determining the contribution of the pixels associated with the object, wherein the selecting of the portion is based on a size, a shape, or particular dimensions of the object.

29. The logic of claim 26, wherein the code is further operable to classify the object as related to the image type if a sum of the contributions of the pixels of the image type exceeds a predetermined threshold, and wherein exceeding the threshold is used to eliminate one of the image types from possible consideration as a correct image type for the object.

30. The logic of claim 26, wherein the code is further operable to:

configure a policy that outlines one or more image types that are prohibited from being transmitted over the network.