Identifying image type in a capture system
View Patent ↗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.
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.