Method and device for converting scanned text to audio data via connection lines and lookup tables

• US 7,675,641 B2
• Filed: 10/28/2004
• Issued: 03/09/2010
• Est. Priority Date: 10/28/2004
• Status: Expired due to Fees

• Current Assignee: Lexmark International Incorporated (Ninestar Corporation)
• Original Assignee: Lexmark International Incorporated (Ninestar Corporation)
• Inventors: Daniel, Stuart Willard, Cui, Chengwu
• Primary Examiner(s): Haskins; Twyler L
• Assistant Examiner(s): Guillermety; Fred
• Application Number:
  US10/975,653
• Publication Number:
  US 20060092480A1
• Time in Patent Office: 1,958 Days
• Field of Search: 358/1.15
• US Class Current: 358/1.15
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: H04N 1/00132 in a digital photofinishing system, i.e. a system where digital photographic images undergo typical photofinishing processing, e.g. printing ordering
• CPC Class Codes: H04N 1/0019 on souvenir-type products or the like, e.g. T-shirts or mugs
• CPC Class Codes: H04N 1/2112 using still video cameras
• CPC Class Codes: H04N 1/2154 the still video camera incorporating a hardcopy reproducing device, e.g. a printer

Abstract

Methods and devices for converting printed media into audio data. In one embodiment, a device includes a scanning platform for supporting the document to be scanned, a scanning mechanism for converting images on the document into image data, and a processor configured to convert the scanned image data into audio data. The device may further include printer components configured to create a hardcopy of the image data, an audio device such as a speaker, and an interface for outputting the image data or audio data.

Claims

1. An apparatus that generates an audio signal from an image, comprising:

a scanning platform for supporting a document to be scanned;

a scanning mechanism for generating computer-readable image data representative of at least a portion of said image; and

a processor configured to convert at least a portion of said computer-readable image data into said audio signal;

wherein said scanning platform, said scanning mechanism and said processor are part of an integrated unit, wherein said processor is additionally configured to create one or more segments within said computer-readable image data that includes a preset identifier and wherein said processor is additionally configured to identify one or more connection lines within said computer-readable image data.

2. The apparatus of claim 1, wherein said processor is additionally configured to associate each of said one or more connection lines with one of said one or more segments and to sequence said segments based at least in part on said one or more connection lines.

3. A method, using a peripheral device to convert an image to an audio signal, comprising:

scanning said image with a scanning mechanism housed within said peripheral device;

generating computer-readable image data based at least in part on said scanned image;

converting said computer-readable image data to an audio signal;

transmitting said audio signal from said peripheral device to an external device;

determining from said computer-readable image data whether said image is a textual image; and

automatically determining a language of said textual image if said image is a textual image;

wherein the converting said computer-readable image data to an audio signal comprises separating said computer readable image data into a plurality of pixel representations and using a lookup table to match each of said pixel representations to an audio equivalent.

4. The method of claim 3, wherein each of said pixel representations corresponds to a letter.

5. The method of claim 3, wherein each of said pixel representations corresponds to a word.

6. The method of claim 3, wherein each of said pixel representations can correspond to either a letter or a word and the language of a text in said image determines whether each of said pixel representations corresponds to a letter or a word.