Systems and methods of image searching

1. A system comprising:

a processing circuit configured to:

receive video content from a media source;

receive a request from a user to select an image from the video content;

store the image in a memory;

determine that the image includes a plurality of items displayed in the image;

conduct a search for known items that each correspond to one of the plurality of items displayed in the image while providing a first visual indication for each of the plurality of items displayed in the image to signify a search status for that item, wherein the first visual indication is modified from a first visual state indicating that the search for the corresponding known item is ongoing to a second visual state indicating that the search for the corresponding known item is completed;

determine, based on the search, that the plurality of items displayed in the image includes a first item having a known identity and a second item having a plurality of known identities;

provide a second visual indication for each of the plurality of items within the selected image to signify an identification status for that item by highlighting the first item and the second item in the image, wherein the highlighting of the first item has a different color than the highlighting of the second item to signify that the first item has the known identity and the second item has the plurality of known identities;

receive a user selection of one of the first item or the second item;

retrieve information about the selected item; and

provide display data, on a display device, in an overlay of the image of the video content, based on the retrieved information, wherein the display data comprises a hyperlink directing the user to their browser on the display device for more information about the selected item.

2. The system of claim 1 , wherein the selection comprises performing a character recognition algorithm on the image to determine textual characters associated with the item displayed in the image.

3. The system of claim 1 , wherein the selection comprises determining the video content has predetermined item identifier data within the video content received from the media source.

4. The system of claim 1 , wherein the image comprises an advertisement associated with an advertiser, the advertisement comprising a hyperlink to a web page associated with the advertiser.

5. The system of claim 1 , wherein the plurality of items displayed in the image comprise at least one of a human face, and object, and a scene.

6. The system of claim 1 , wherein the processing circuit is further configured to identify a text region of the image by:

dividing the image into a plurality of regions;

detecting features in each region of the plurality of regions;

analyzing detected features in each region; and

determining whether the detected features comprises text.

7. The system of claim 1 , wherein the processing circuit is further configured to:

search for identities of the plurality of selected items, wherein the search comprises sending image data to an image matching module;

receive a report from the image matching module based on the search;

if an identity is found for an item based on the report, determine that the item is a first item having a known identity;

if an identity is not found for an item based on the report, determine that the item is a second item having an unknown identity or that the second item has a plurality of known identities.

8. A method comprising:

receiving, at a processor, video content from a media source;

receiving, at a processor, a request from a user via a pause command to select an image from the video content;

storing the image in a memory;

determining that the image includes a plurality of items displayed in the image;

conducting a search for known items that each correspond to one of the plurality of items displayed in the image while providing a first visual indication for each of the plurality of items displayed in the image to signify a search status for that item, wherein the first visual indication is modified from a first visual state indicating that the search for the corresponding known item is ongoing to a second visual state indicating that the search for the corresponding known item is completed;

determining, based on the search, that the plurality of items displayed in the image includes a first item having a known identity and a second item having a plurality of known identities;

providing a second visual indication for each of the plurality of items within the selected image to signify an identification status for that item by highlighting the first item and the second item in the image, wherein the highlighting of the first item has a different color than the highlighting of the second item to signify that the first item has the known identity and the second item has the plurality of known identities;

receiving, at the processor, a user selection of the first or the second item;

retrieving information about the selected item; and

providing display data, on a display device, in an overlay of the image of the video content based on the retrieved information, wherein the display data comprises a hyperlink directing the user to their browser on the display device for more information about the selected item.

9. The method of claim 8 , wherein the selection comprises performing a character recognition algorithm on the image to determine textual characters associated with the items displayed in the image.

10. The method of claim 8 , wherein the selection comprises determining the video content has predetermined item identifier data within the video content received from the media source.

11. The method of claim 8 , wherein the image comprises an advertisement associated with an advertiser, the advertisement comprising a hyperlink to a web site associated with the advertiser.

12. The method of claim 8 , wherein the plurality of items displayed in the image comprise at least one of a human face, object, and a scene.

13. The method of claim 8 , further comprising identifying a text region of the image by: dividing the image into a plurality of regions; detecting features in each region of the plurality of regions; analyzing detected features in each region; and determining whether the detected features comprise text.

14. The system of claim 1 , wherein the information about the selected item comprises information about each of the plurality of known identities, and wherein the processing circuit is further configured to:

receive a second user selection of one of the plurality of known identities; and

retrieve additional information about the selected one of the plurality of known identities.

15. The method of claim 8 , wherein the information about the selected item comprises information about at least one of the plurality of known identities, and the method further comprises:

receiving a second user selection of one of the plurality of known identities; and

retrieving additional information about the selected one of the plurality of known identities.