Autogenerating video from text

• US 10,402,637 B2
• Filed: 01/19/2017
• Issued: 09/03/2019
• Est. Priority Date: 01/20/2012
• Status: Active Grant

• Current Assignee: Elwha LLC (Intellectual Ventures LLC)
• Original Assignee: Elwha LLC (Intellectual Ventures LLC)
• Inventors: Chan, Alistair K., Gates, William, Holman, Pablos, Hyde, Roderick A., Jung, Edward K. Y., Kare, Jordin T., Myhrvold, Nathan P., Rosema, Keith David, Tegreene, Clarence T., Wood, Jr., Lowell L.
• Primary Examiner(s): Couso, Jose L
• Application Number:
  US15/410,002
• Publication Number:
  US 20170132461A1
• Time in Patent Office: 957 Days
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 13/00 Animation
• CPC Class Codes: G06T 15/00 3D [Three Dimensional] image rendering
• CPC Class Codes: G06V 10/17 using hand-held instruments
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition

Abstract

A method of converting user-selected printed text to a synthesized image sequence is provided. The method includes capturing a first image of printed text and generating a model information associated with the text.

Claims

1. A method of converting user-selected printed text to a synthesized image sequence, comprising:

capturing a first image of printed text;

generating, by a server in response to capturing the first image of printed text, model information that is representative of the printed text based on auxiliary information and a data preference file; and

generating, by the server, a synthesized image sequence based on the model information;

wherein the data preference file indicates user preferences to be applied when the synthesized image sequence is generated.

2. The method of claim 1, further comprising capturing the first image by camera.

3. The method of claim 2, wherein the camera is coupled to a personal electronic device.

4. The method of claim 1, further comprising translating the text of the first image into a machine readable format.

5. The method of claim 4, further comprising generating model information based on the text translated into the machine readable format.

6. The method of claim 1, wherein the auxiliary information comprises the source of the printed text contained in the first image and information associated with the author of the source of the text, wherein the source is the origin of the printed text.

7. The method of claim 1, further comprising receiving the preference data file from another user.

8. The method of claim 1, further comprising generating the preference data file based on a previously generated preference data file.

9. A computerized method of sharing a synthesized image sequence generated from user-selected text, comprising:

capturing an image;

acquiring a textual passage from a machine readable text contained in the image;

generating, by a server in response to acquiring the textual passage, model information that is representative of the textual passage; and

exporting a file, the file configured to enable another system for another user to generate a synthesized image sequence associated with the textual passage;

wherein the file comprises the model information.

10. The method of claim 9, wherein capturing the image includes capturing the image by camera.

11. The method of claim 10, wherein the camera is coupled to a personal electronic device.

12. The method of claim 10, wherein the camera is coupled to a mobile phone.

13. The method of claim 9, wherein the file comprises the synthesized image sequence.

14. The method of claim 9, further comprising generating the synthesized image sequence based on the file.

15. The method of claim 9, wherein the file is exported from a first computer;

and

further comprising causing an indication to be displayed on a second computer in relation to a copy of the textual passage, the indication indicating availability of a file to generate a synthesized image sequence for that passage.

16. A computerized method of converting a textual passage to a synthesized image sequence, comprising:

determining a first textual passage currently being read by a user;

predicting a second textual passage that will be read by the user;

generating an indicia in relation to the second textual passage; and

generating a synthesized image sequence associated with the second textual passage.

17. The method of claim 16, wherein the indicia indicates that a synthesized image sequence has been generated for the second textual passage.

18. The method of claim 16, wherein the indicia indicates a predicted time to complete generation of a synthesized image sequence for the second textual passage.

19. The method of claim 16, wherein the indicia indicates a predicted time until a synthesized image sequence for the second textual passage can begin playing.

20. The method of claim 16, further comprising predicting the second textual passage based on the amount of text between the first textual passage and the second textual passage.

21. The method of claim 16, further comprising predicting the second textual passage that will be read by the user based on the reading speed of the user.

22. The method of claim 21, further comprising predicting the second textual passage that will be read by the user based on an image synthesization speed of a processing electronics.

23. The method of claim 16, further comprising generating a synthesized image sequence at a quality level based on a predicted time until the user reads the second textual passage.

24. The method of claim 16, further comprising predicting a third textual passage that will be read by the user.