Granted Patent B2

US 9,218,680 · App. 13/222,594 · Granted Dec 22, 2015

Inventors: Raymond C. Kurzweil (Newton, MA); Paul Albrecht (Bedford, MA); Peter Chapman (Bedford, MA); Jeff Brewer (Wellesley, MA)

Assignee: K-NFB Reading Technology, Inc.

G06T11/60

Abstract

Claims (86)

1. A computer-implemented method, comprising:

determining by the computer portions of a page that include glyphs, where glyphs are text-based, character-based, or symbol-based content, and where glyphs exclude graphic-based content;

generating by the computer an image of the page that has only non-glyph graphical content in the image;

classifying the glyphs into visible glyphs and non-visible glyphs;

removing by the computer the non-visible glyphs; and

rendering the image of the page, with the visible glyphs rendered as an overlay on the image of the page.

2. The method of claim 1 , wherein rendering the visible glyphs as an overlay on the image of the page when rendering the page comprises aligning by the computer the visible glyphs with the image of the non-glyph portions of the page when rendering the page, based on with positional and size information that associates the glyph elements to respective locations in the image representation of the document as rendered by a device that renders the image of the page with the visible glyphs.

3. The method of claim 1 , wherein the image is a bitmap.

4. The method of claim 1 , wherein classifying the glyphs comprises determining if a glyph is hidden by an image or graphic.

5. The method of claim 1 , wherein classifying the glyphs comprises:

changing a property associated with at least one of the glyphs to a first value;

generating a first image of the page based on the first value of the property;

changing the property of at least one of the glyphs to a second, different value;

generating a second image of the page based on the second value of the property; and

comparing the first and second images to detect differences in the property of the glyphs between the first and the second images.

6. The method of claim 1 , wherein classifying the glyphs comprises:

changing a property associated with all of the glyphs to a first value;

generating a first image of the page based on the first value of the property;

changing the property of all glyphs to a second, different value;

generating a second image of the page based on the second value of the property; and

comparing the first and second images to detect differences in the property of the glyphs between the first and the second images.

7. The method of claim 1 , wherein classifying the glyphs comprises:

changing the color of all glyphs to a first color;

generating a first image of the page;

changing the color of all glyphs to a second color;

generating a second image of the page; and

comparing the first and second images to detect differences in the colors of the glyphs between the first and the second images.

8. The method of claim 7 , wherein comparing the first and second images comprises determining portions where the first and second images differ.

9. The method of claim 1 , further comprising using speech-to-text processing to generate an audio output of the visible glyphs.

10. A system, comprising:

one or more processors configured to:

determine portions of a page that includes glyphs, where glyphs are text-based, character-based, or symbol-based content, and where glyphs exclude graphic content;

generate a single image of the page that has only all non-glyph graphical content in the image;

classify the glyphs into visible glyphs and non-visible glyphs;

remove the non-visible glyphs; and

overlay the visible glyphs on top of the image when rendering the page.

11. The system of claim 10 , wherein the image is a bitmap.

12. The system of claim 10 , wherein the configurations to classify the glyphs comprise configurations to determine if a glyph is hidden by an image or graphic.

13. The system of claim 10 , wherein the configurations to classify the glyphs comprise configurations to:

change a property associated with all glyphs to a first value;

generate a first image of the page based on the first value of the property;

change the property of all glyphs to a second, different value;

generate a second image of the page based on the second value of the property; and

compare the first and second images to detect differences in the property of the glyphs between the first and the second images.

14. The system of claim 10 , wherein the configurations to classify the glyphs comprise configurations to:

change the color of all glyphs to a first color;

generate a first image of the page;

change the color of all glyphs to a second color;

generate a second image of the page; and

compare the first and second images to detect differences in the colors of the glyphs between the first and the second images.

15. The system of claim 10 , further comprising a speech-to-text unit configured to use speech-to-text processing to generate an audio output of the visible glyphs.

16. A computer program product tangibly stored in a computer readable hardware storage device, the computer program product comprising instructions to cause a processor to:

determine portions of a page that include glyphs, where glyphs are text-based, character-based, or symbol-based content, and where glyphs exclude graphic content;

generate an image of the page that has only non-glyph graphical content associated in the image;

classify the glyphs into visible glyphs and non-visible glyphs;

remove the non-visible glyphs; and

overlay the visible glyphs on top of the image when rendering the page.

17. The computer program product of claim 16 , wherein the instructions to classify the glyphs comprise instructions to determine if a glyph is hidden by an image or graphic.

18. The computer program product of claim 16 , wherein the instructions to classify the glyphs comprise instructions to:

change a property associated with all glyphs to a first value;

generate a first image of the page based on the first value of the property;

change the property of all glyphs to a second, different value;

generate a second image of the page based on the second value of the property; and

compare the first and second images to detect differences in the property of the glyphs between the first and the second images.

19. The computer program product of claim 16 , wherein the instructions to classify the glyphs comprise instructions to:

change the color of all glyphs to a first color;

generate a first image of the page;

change the color of all glyphs to a second color;

generate a second image of the page; and

compare the first and second images to detect differences in the colors of the glyphs between the first and the second images.

20. A computer implemented method, the method comprising:

determining by a computer portions of a page that include glyphs, where glyphs are text-based, character-based, or symbol-based content and exclude graphic content;

classifying by the computer the glyphs into visible glyphs and non-visible glyphs by:

changing by the computer a property associated with at least one of the glyphs to a first value;

generating by the computer a first image of the page based on the first value of the property;

changing by the computer the property of at least one of the all glyphs to a second, different value;

generating by the computer a second image of the page based on the second value of the property; and

comparing by the computer the first and second images to detect differences in the property of the glyphs between the first and the second images.

21. The method of claim 20 , wherein:

changing a property associated with at least one of the glyphs to a first value comprises changing a property associated with all of the glyphs to the first value; and

changing the property of at least one of the all glyphs to a second, different value comprises changing the property of all glyphs to the second, different value.

22. The method of claim 20 , wherein:

changing a property associated with at least one of the glyphs to a first value comprises changing the color of at least one of the glyphs to a first color;

changing the property of at least one of the all glyphs to a second, different value comprises changing the color of at least one of the glyphs to a second.

23. The method of claim 20 , wherein comparing the first and second images comprises determining portions where the first and second images differ.

24. The method of claim 20 , further comprising using speech-to-text processing to generate an audio output of the visible glyphs.

Assignments (8)

Continuity (2)