Image Tagging System
An image recognition approach employs both computer generated and manual image reviews to generate image tags characterizing an image. The computer generated and manual image reviews can be performed sequentially or in parallel. The generated image tags may be provided to a requester in real-time, be used to select an advertisement, and/or be used as the basis of an internet search. In some embodiments generated image tags are used as a basis for an upgraded image review. A confidence of a computer generated image review may be used to determine whether or not to perform a manual image review.
1 . An image processing system comprising:
an I/O configured to receive an image over a communication network;
an image ranker configured to determine a priority of the image and to determine whether or not to manually tag the image based on the priority;
means for tagging the image to produce one or more image tags characterizing the image;
memory configured to store the image and the one or more image tags characterizing the image, in a data structure; and
a microprocessor configured to execute at least the image ranker.
2 . The system of claim 1 , wherein the means for tagging the image include at least an automatic identification interface configured to communicate the image to an automatic identification system and also image posting logic configured to post the image to a human reviewer.
3 . The system of claim 1 , further comprising an advertising system configured to assign advertisements to the image based on the one or more image tags.
4 . The system of claim 1 , wherein the image ranker is further configured to determine the priority of the image based on one or more image tags of a computer generated review of the image.
5 . The system of claim 1 , wherein the image ranker is further configured to select between tagging the image automatically and not tagging the image automatically, based on the priority of the image.
6 . The system of claim 1 , wherein the image ranker is further configured to determine the priority of the image based on a confidence that one or more image tags of a computer generated review of the image correctly identify the contents of the image.
7 . The system of claim 1 , wherein the image ranker is further configured to determine the priority of the image based on how often a webpage including the image is viewed.
8 . The system of claim 1 , wherein the image ranker is further configured to determine the priority based on a source of the image.
9 . The system of claim 1 , wherein the image ranker is further configured to determine the priority of the image based on text included on a same webpage as the image.
10 . The system of claim 1 , wherein the image ranker is further configured to determine the priority of the image based on a ranking of a webpage including the image.
11 . An image processing system comprising:
an I/O configured to receive an image over a communication network;
an image ranker configured to determine a priority of the image and to select a process of tagging the image based on the priority;
means for tagging the image to produce one or more image tags characterizing the image;
memory configured to store the image and the one or more image tags characterizing the image, in a data structure; and
a microprocessor configured to execute at least the image ranker.
12 . The system of claim 11 , wherein the means for tagging the image include at least an automatic identification interface configured to communicate the image to an automatic identification system and also image posting logic configured to post the image to a human reviewer.
13 . The system of claim 11 , further comprising an advertising system configured to assign advertisements to the image based on the one or more image tags.
14 . The system of claim 11 , wherein the image ranker is further configured to select between an automated process of tagging the image and a manual process of tagging the image.
15 . The system of claim 11 , further comprising content processing logic configured to extract the image from an image source, wherein the image source includes a website.
16 . An image processing system comprising:
an I/O configured to communicate an image and image tags over a communication network;
an image ranker configured to determine a priority for tagging the image based on how many times a video including the image is viewed;
destination logic configured to determine a destination to send the image to, for a manual review of the image by a human reviewer;
image posting logic configured to post the image to the destination;
review logic configured to receive the manual review of the image from the destination, the manual review including one or more image tags identifying contents of the image;
memory configured to store the one or more image tags in a data structure; and
a microprocessor configured to execute at least the image ranker.
17 . The system of claim 16 , wherein the I/O is further configured to receive the video including the image.
18 . The system of claim 16 , wherein the image ranker is further configured to determine a priority for manually tagging the image based on a value of one or more image tags generated using automated analysis of the image.
19 . The system of claim 16 , wherein the image ranker is further configured to determine a priority for manually tagging the image based on a measure of confidence that tags generated using an automated analysis of the image are correct.
20 . The system of claim 16 , wherein the image ranker is further configured to determine a priority for manually tagging the image based on a description of the video.
21 . The system of claim 16 , further comprising an advertising system configured to select an advertisement based on the one or more image tags identifying contents of the image.
22 . The system of claim 21 , wherein the advertising system is further configured to present the advertisement in association with the video.
23 . The system of claim 16 , wherein the one or more image tags identifying contents of the image identify an action within the video.