Autogenerating video from text

• US 8,731,339 B2
• Filed: 01/20/2012
• Issued: 05/20/2014
• Est. Priority Date: 01/20/2012
• Status: Expired due to Fees

• Current Assignee: Elwha LLC (Intellectual Ventures LLC)
• Original Assignee: Elwha LLC (Intellectual Ventures LLC)
• Inventors: Chan, Alistair K., Gates, William, Holman, Paul, Hyde, Roderick A., Jung, Edward K. Y., Kare, Jordin T., Myhrvold, Nathan P., Rosema, Keith David, Wood, Lowell L. Jr., Tegreene, Clarence T.
• Primary Examiner(s): COUSO, JOSE L
• Application Number:
  US13/355,194
• Publication Number:
  US 20130188887A1
• Time in Patent Office: 851 Days
• Field of Search: 382/229, 382/312, 345/473, 345/156, 345/625, 345/632, 345/634, 715/210, 715/255, 715/706, 715/708, 715/716, 715/720, 715/722, 715/723, 706/11, 706/45, 434/317, 386/232, 386/281, 463/1, 463/29, 463/30, 725/62, 707/999.104, 707/999.107, 704/9, 704/257, 704/260, 704/270, 704/276
• US Class Current: 382/312
• 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 system for converting user-selected printed text to a synthesized image sequence, comprising:

processing electronics configured to receive an image of text over a network, the text being a passage from a source text, to translate the text of the image of text into a machine readable format, and, in response to receiving the image;

to determine the source text from the text;

to search for and to receive, from a source other than the image of text, auxiliary information comprising another passage within the source text; and

to generate model information based on the auxiliary information and the text translated into the machine readable format.

2. The system of claim 1, wherein the image of text is received from a personal electronic device.

3. The system of claim 1, wherein the processing electronics are further configured to receive a text selection information before translating the image, the text selection information comprising a subset of the text in the image of the text.

4. The system of claim 1, wherein receiving the image comprises receiving a text selection information.

5. The system of claim 1, wherein the processing electronics are further configured to generate the model information based on a contextual cue.

6. The system of claim 1, wherein the processing electronics are further configured to analyze the text for a contextual cue.

7. The system of claim 1, wherein the processing electronics are further configured to generate the model information based on auxiliary information.

8. The system of claim 7, wherein the processing electronics are further configured to receive auxiliary information.

9. The system of claim 1, wherein the processing electronics are further configured to generate the model information based on a preference data file.

10. The system of claim 9, wherein the processing electronics are further configured to receive a preference data file from another user.

11. The system of claim 9, wherein the processing electronics are further configured to generate a preference data file based on a previously generated preference data file.

12. The system of claim 1, wherein the processing electronics are further configured to generate a synthesized image sequence based on the model information.

13. The system of claim 12, wherein the processing electronics are further configured to cause the synthesized image sequence to be displayed on a designated display.

14. The system of claim 13, wherein the designated display is located remotely from the processing electronics over a network.

15. The system of claim 12, wherein the processing electronics are configured to generate the synthesized image sequence based on a previously generated model information.

16. The system of claim 15, wherein the processing electronics are configured to receive the previously generated model information.

28. The system of claim 1, wherein the model information includes instructions relating to an orientation, a motion, and an interaction of one or more objects.

29. The system of claim 28, wherein the processing electronics are further configured to render a synthesized image sequence based on the model information.

30. The system of claim 1, wherein the processing electronics are further configured to translate the image of text using optical character recognition.

31. The system of claim 1, wherein the processing electronics are further configured to translate the image of text using a handwriting recognition engine.

32. The system of claim 4, wherein the text selection information comprises an identification of a portion of the textual passage.

33. The system of claim 6, wherein the contextual cue comprises at least one of a setting, a character, an action, and a pose;

and

wherein the processing electronics are further configured to generate the model information based on a contextual cue.

34. The system of claim 9, wherein the preference data file comprises a time period information, wherein the time period information comprises a historical era.

35. The system of claim 9, wherein the preference data file comprises a linguistic information.

17. A system for converting a textual passage to a synthesized image sequence, comprising:

processing electronics configured to;

generate a model information based on a preference data file and a textual passage in response to the textual passage being written, the model information including instructions relating to an orientation, a motion, and an interaction of one or more objects, and the preference data file including a time period information, wherein the time period information comprises a historical era; and

render a synthesized image sequence based on the model information.

18. The system of claim 17, wherein the processing electronics are further configured to receive the textual passage from a user input device.

19. The system of claim 17, wherein the processing electronics are further configured to automatically generate the model information upon receiving a signal indicating the end of a paragraph.

20. The system of claim 19, wherein the processing electronics are further configured to automatically generate updated model information upon receiving a signal indicating the end of a second paragraph, and to render a synthesized image sequence based on the updated model information.

21. The system of claim 17, wherein the processing electronics are further configured to receive an image of the textual passage.

22. The system of claim 21, wherein the processing electronics are further configured to translate the textual passage into a machine readable format using a handwriting recognition engine.

23. The system of claim 17, wherein the processing electronics are further configured to generate the model information based on a contextual cue.

24. The system of claim 23, wherein the processing electronics are further configured to analyze the textual passage for a contextual cue.

25. The system of claim 17, wherein the processing electronics are further configured to generate the model information based on auxiliary information.

26. The system of claim 17, wherein the processing electronics are further configured to generate the synthesized image sequence based on a preference data file.

27. The system of claim 17, further comprising a outputting the synthesized image sequence to a display.