Image processing including streaming image output
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. Images and their associated image tags are optionally added to an image sequence.
1. A method of generating a stream of images, the method comprising:
receiving a first image from a first remote client;
posting the first image to an automatic identification system configured to identify contents of the first image and to provide one or more first image tags that characterize these contents;
receiving a second image from a second remote client;
posting the second image to an automatic identification system configured to identify contents of the second image and to provide one or more second image tags that characterize these contents;
adding the first image and the second image to an image sequence; and
providing the image sequence to a third remote client.
2. The method of claim 1 , further comprising sending the one or more first image tags to the first remote client.
3. The method of claim 1 , further comprising sending the first image to a human image reviewer and receiving one or more third image tags from the human image reviewer.
4. The method of claim 3 , wherein sending the first image to the human image reviewer is responsive to a measure of confidence that the one or more first image tags accurately characterize the contents of the first image.
5. The method of claim 3 , further comprising sending the one or more third image tags to the first remote client.
6. The method of claim 1 , further comprising selecting the first image for addition to the image sequence based on the first image tags or the third image tags.
7. The method of claim 1 , further comprising selecting the first image for addition to the image sequence based on an account associated with the first remote client.
8. The method of claim 1 , further comprising selecting the first image for addition to the image sequence based on comments provided about the first image.
9. The method of claim 1 , wherein adding the first image to the image sequence includes adding the first image to several frames of a video.
10. The method of claim 1 , wherein adding the first image to the image sequence includes providing the first image to an application configured to automatically show the first and second images in succession.
11. The method of claim 1 , wherein adding the first image to the image sequence is responsive to a popularity measure for the first image.
12. The method of claim 11 , wherein in the popularity measure is calculated based on a number of favorable responses for the first image.
13. The method of claim 1 , further comprising adding an advertisement to the image sequence.
14. The method of claim 13 , further comprising selecting the advertisement based on the one or more first image tags.
15. The method of claim 13 , further comprising selecting the advertisement based on an account associated with the first remote client.
16. The method of claim 13 , further comprising selecting the advertisement based on data automatically retrieved from a social network account of the first remote client.
17. The method of claim 1 , wherein the first image is added to the image sequence such that the first image is in a segment of the image sequence having a duration of between 2 and 10 seconds.
18. The method of claim 1 , wherein the image sequence is provided to the third remote client one image at a time.
19. The method of claim 1 , wherein the image sequence is provided to the third remote client as compressed video.