Method and System to Convert Visually Orientated Objects to Embedded Text

• US 20120192059A1
• Filed: 01/20/2011
• Published: 07/26/2012
• Est. Priority Date: 01/20/2011
• Status: Active Grant

• Current Assignee: Vastec, Inc.
• Original Assignee: Vastec, Inc.
• Inventors: Reinpoldt, Willem H. III, Laskaris, Lucas George
• Granted Patent: US 8,832,541 B2
• Time in Patent Office: Days
• US Class Current: 715/231
• CPC Class Codes: G06F 40/151 Transformation
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06V 2201/09 Recognition of logos
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G09B 21/006 using audible presentation of the information
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

A method to convert visually orientated objects to embedded text is disclosed. In a particular embodiment, the method includes scanning an electronically stored document, identifying at least one visually orientated object within the document, analyzing the at least one visually orientated object to generate a textual description of the at least one visually orientated object, and embedding the textual description within the electronically stored document, and storing a converted document with the embedded textual description for distribution to users of text to speech synthesizers and Braille output devices. In addition, the method includes identifying text characters within the at least one visually orientated object. The text characters within the at least one visually orientated object are used in generating the textual description of the visually orientated object. A color of the textual description embedded within the electronic document is a background color of the electronic document and visually undetectable.

Claims

1. A method to convert a visually orientated object to embedded text, the method comprising:

scanning an electronically stored document;

identifying at least one visually orientated object within the document;

analyzing the at least one visually orientated object to generate a textual description of the at least one visually orientated object; and

embedding the textual description within the electronically stored document.

2. The method of claim 1, further comprising saving the electronically stored document with the textual description as a converted document.

3. The method of claim 2, further comprising identifying text characters within the at least one visually orientated object.

4. The method of claim 3, further comprising using the text characters within the at least one visually orientated object in generating the textual description of the visually orientated object.

5. The method of claim 4, wherein a color of the textual description embedded within the electronic document is a background color of the electronic document or transparent, and visually undetectable.

6. The method of claim 5, wherein placement of the textual description embedded within the document is proximate to the at least one visually orientated object.

7. The method of claim 6, wherein a font size, typographic character attribute, paragraph attribute, page attribute, or any combination thereof, of the textual description is adjusted to minimize an impact to the aesthetics of the document.

8. The method of claim 7, further comprising determining whether the at least one visually orientated object is a photograph, graphic image, signature, zip code, phone number, abbreviation, or any combination thereof.

9. A non-transitory processor readable medium having processor instructions that are executable to cause a processor to:

scan an electronically stored document;

identify at least one visually orientated object within the document;

analyze the at least one visually orientated object to generate a textual description of the at least one visually orientated object; and

embed the textual description within the electronically stored document.

10. The non-transitory processor readable medium of claim 9, wherein the processor executable instructions are further executable to save the electronically stored document as a converted document.

11. The non-transitory processor readable medium of claim 10, wherein the processor executable instructions are further executable to identify text characters within the at least one visually orientated object.

12. The non-transitory processor readable medium of claim 11, wherein the processor executable instructions are further executable to use the text characters within the at least one visually orientated object in generating the textual description of the visually orientated object.

13. The non-transitory processor readable medium of claim 12, wherein a color of the textual description embedded within the electronic document is a background color of the electronic document or transparent, and visually undetectable.

14. The non-transitory processor readable medium of claim 13, wherein placement of the textual description embedded within the document is proximate to the at least one visually orientated object.

15. The non-transitory processor readable medium of claim 14, wherein a font size, typographic character attribute, paragraph attribute, page attribute, or any combination thereof of the textual description is adjusted to minimize an impact to the aesthetics of the document.

16. The non-transitory processor readable medium of claim 15, wherein the processor executable instructions are further executable to determine whether the at least one visually orientated object is a photograph, graphic image, signature, zip code, phone number, abbreviation, or any combination thereof.

17. A system to convert a visually orientated object to speech, the system comprising:

an electronically stored document;

a scanning software module to scan the at least one electronically stored document;

an identification software module to identify at least one visually orientated object within the document;

an analysis software module to analyze the at least one visually orientated object to generate a textual description of the at least one visually orientated object;

an insertion module to embed the textual description within the electronically stored document; and

a converted document having the embedded textual description, wherein the converted document is adapted for distribution to users of text to speech synthesizers and Braille output devices.

18. The system of claim 17, wherein a color of the textual description embedded within the electronic document is a background color of the electronic document or transparent, and visually undetectable.

19. The system of claim 18, wherein placement of the textual description embedded within the document is proximate to the at least one visually orientated object.

20. The system of claim 19, wherein a font size, typographic character attribute, paragraph attribute, page attribute, or any combination thereof, of the textual description is adjusted to minimize an impact to the aesthetics of the document.