Training a user on an accessiblity device

• US 8,154,771 B2
• Filed: 01/29/2008
• Issued: 04/10/2012
• Est. Priority Date: 01/29/2008
• Status: Active Grant

• Current Assignee: National Federation of the Blind
• Original Assignee: K-NFB Reading Technology Inc.
• Inventors: Albrecht, Paul, Zetune, Rafael Maya, Gibson, Lucy, Kurzweil, Raymond C., Krishnamachari, Srivathsan
• Primary Examiner(s): PERUNGAVOOR, SATHYANARAYA V
• Application Number:
  US12/021,925
• Publication Number:
  US 20090190838A1
• Time in Patent Office: 1,533 Days
• Field of Search: 358/406
• US Class Current: 358/406
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• 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 30/1448 based on markings or identifiers characterising the document or the area
• CPC Class Codes: G06V 30/1475 Inclination or skew detection or correction of characters or of image to be recognised
• CPC Class Codes: G09B 19/003 Repetitive work cycles; Sequence of movements
• CPC Class Codes: G09B 21/00 Teaching, or communicating with, the blind, deaf or mute audible presentation of material to be studied G09B5/04; devices or methods for replacing direct visual or auditory perception by another kind of perception A61F9/08, A61F11/04; audible indication of meter readings or of colour G01D7/12; watches for blind persons G04B25/02; speech analysis, speech recognition G10L; sound-recording or reproducing, per se G11B
• CPC Class Codes: G09B 21/006 using audible presentation of the information

Abstract

A user of an accessibility device is taught to properly use the device with a test image such that the accessibility device captures the entirety of or a large portion of a test image. In training the user, the device processes test image'"'"'s information located within the device'"'"'s field of view. Based on this processed information, the device indicates to the user if the device should be re-positioned such that a larger portion of the test image comes within the device'"'"'s field of view.

Claims

1. A method executed in a reading machine, the method comprising:

comparing by the reading machine a received image of a test page to a known image of the test page stored in the reading machine, with the test page having unique information, by;

performing text recognition on the captured image; and

comparing text of the captured image to text of the known image;

computing by the reading machine differences in text recognized in the received image compared to the known image; and

calculating by the reading machine a new placement of an image input device that provides the received image to the reading machine relative to the test page such that the received image of the test page better approximates the known image, with the new calculated placement of the reading machine includes an angle of tilt of the reading machine in at least one of X, Y, or Z directions.

2. The method of claim 1, further comprising:

producing an indication to inform the user of the new placement of the image input device that provides the received image to the reading machine.

3. The method of claim 2 further comprising:

determining an order to inform the user of the placement by at least one of a type of difference or a magnitude of difference between the captured image and the known image.

4. The method of claim 1 wherein the reading machine is a portable reading machine carrying the image input device, and as the user adjusts the placement of the portable reading machine the portable reading machine calculates subsequent placements until an actual placement provides a received image that substantially matches the known image.

5. The method of claim 1 wherein the reading machine automatically detects that it is in teaching mode.

6. The method of claim 1 wherein the new calculated placement of the reading machine comprises coordinates relative to the known image in at least one of X, Y, or Z planar fields.

7. The method of claim 1 wherein the tilt of the reading machine is determined using an accelerometer.

8. The method of claim 1 wherein the known image is at least comprised of words of different sizes.

9. The method of claim 1 wherein the known image is at least comprised of strings of numbers.

10. The method of claim 9 wherein the strings of numbers are located at a top, middle, and bottom of the known image.

11. The method of claim 10 further comprising:

recalculating placement until the captured image includes the strings of numbers at the top, middle and bottom of the captured image.

12. The method of claim 1 wherein if text recognition cannot be performed on part of the captured image, the reading machine provides an indication to the user to check a condition of a lens on the reading machine.

13. A computer program product tangibly embodied on a computer readable storage device for training a user on a reading machine, the computer program product comprising instructions for causing the reading machine to:

compare a received image of a test page to a known image of the test page stored in the reading machine, with the test page having unique information, by instructions to;

perform text recognition on the captured image; and

compare text of the captured image to text of the known image; and

compute differences in text recognized in the received image compared to the known image; and

calculate a new placement of an image input device that provides the received image to the reading machine such that the received image of the test page better approximates the known image, with the new calculated placement of the reading machine includes an angle of tilt of the reading machine in at least one of X, Y, or Z directions.

14. The computer program product of claim 13, further comprising instructions to:

render an indication to inform the user of the new placement of the reading machine.

15. The computer program product of claim 13, further comprising instructions to:

determine an order to inform the user of the placement by at least one of a type of difference or a magnitude of difference between the captured image and the known image.

16. The computer program product of claim 13 wherein the known image is at least comprised of strings of numbers located at a top, middle, and bottom of the known image.

17. The computer program product of claim 13, further comprising instructions to:

recalculate placement of the reader until the captured image includes the strings of numbers at the top, middle and bottom of the captured image.

18. The computer program product of claim 13 wherein if text recognition cannot be performed on part of the captured image, the computer program product produces an indication to advise the user to check a condition of a lens on the reading machine.

19. A portable reading machine comprising:

an image input device for capturing images;

a computing device coupled to the image input device, the computing device, comprising;

a processor to execute instructions; and

a computer program product residing on a computer readable medium, the computer program product comprising instructions for causing the processor to;

process the captured images to;

compare at least one of the captured images of a test page to a known image of the test page stored in the reading machine, by instructions to;

perform text recognition on the captured image; and

compare text of the captured image to text of the known image; and

in text recognized in the captured image compared to the known image; and

calculate new placement information of the reading machine relative to the test page such that the captured image better approximates the known image, with the new calculated placement of the reading machine includes an angle of tilt of the reading machine in at least one of X, Y, or Z directions.

20. The reading machine of claim 19 wherein the computer program product comprises instructions to:

inform a user of the calculated placement information.

21. The reading machine of claim 19 wherein the information is placement coordinates and the computer program product comprises instructions to:

calculate current placement coordinates of the reading machine relative to the known image; and

render instructions to inform the user of the calculated placement coordinates in an order determined by at least one of a type of difference or a magnitude of difference between the captured image and the known image.

22. The reading machine of claim 19 wherein the computer program product comprises instructions to:

automatically detect that the reading machine is in training mode.

23. The reading machine of claim 22 wherein the known image is provided from capturing the image from a glossy, laminated sheet containing strings of characters, the strings of character located at a top, middle, and bottom of the laminated sheet.

24. The reading machine of claim 19 wherein the test page and the known image are at least comprised of strings of characters, the strings of characters located at a top, middle, and bottom of the known image.

25. The reading machine of claim 24 wherein the computer program product further receives instructions to:

recalculate the placement coordinates until the captured image includes the strings of numbers at the top, middle and bottom of the captured image.

26. The reading machine of claim 24 wherein the computer program product further receives instructions to:

recalculate the placement coordinates by determining if the numbers at the top, middle or bottom of the known image are missing from the captured image.

27. The reading machine of claim 19 wherein the computer program product further comprises instructions to:

recalculate the placement coordinates, if text recognition cannot be performed on part of the captured image, such that the captured image includes more of the known image.

28. The reading machine of claim 19 wherein if text recognition cannot be performed on part of the captured image, the reading machine produces an indication to advise the user to check a condition of a lens on the reading machine.

29. The reading machine, of claim 19 further comprising the test page with the test page being:

a sheet, having at least three strings of numbers printed across spaced portions of a top, middle and bottom of one surface of the page and strings of characters of different sizes printed across the opposing surface of the page and with one corner of the page diagonally cut off.