PROCESSING OF IMAGES DURING ASSESSMENT OF SUITABILITY OF BOOKS FOR CONVERSION TO AUDIO FORMAT

• US 20160042230A1
• Filed: 10/22/2015
• Published: 02/11/2016
• Est. Priority Date: 01/24/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Conboy, Garth, Morton, Michael Salomon
• Granted Patent: US 9,613,268 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/133 Evaluation of quality of the acquired characters
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

A system to process graphical elements within a book during assessment of the book for suitability for conversion to an audio format includes an image classification subsystem, an image processing subsystem, and a weighting subsystem. The image classification subsystem is configured to classify a graphical element based on at least one of a context of the graphical element and properties of the graphical element. The image processing subsystem is configured process the graphical element to create a processed graphical element, the processing responsive to the classification of the graphical element. The weighting subsystem is configured to produce a weighting corresponding to the processed graphical element, the weighting indicating an impact of the graphical element of suitability of the book for conversion to the audio format.

Claims

1. A system to process graphical elements within a book during assessment of the book for suitability for conversion to an audio format, the system comprising:

an image classification subsystem configured to classify a graphical element based on at least one of a context of the graphical element and properties of the graphical element;

an image processing subsystem operably connected to the image classification subsystem and configured to process the graphical element to create a processed graphical element, the processing responsive to the classification of the graphical element; and

a weighting subsystem operably connected to the image processing subsystem and configured to produce a weighting corresponding to the processed graphical element, the weighting indicating an impact of the graphical element of suitability of the book for conversion to the audio format.

2. The system of claim 1, wherein, responsive to the classification of the graphical element indicating the graphical element corresponds to text, the image processing system creates the processed graphical element by replacing the graphical element with corresponding text.

3. The system of claim 2, wherein the corresponding text is based on the context of the graphical element.

4. The system of claim 1, wherein the graphical element is a symbol without a corresponding Unicode character, the image processing subsystem is further configured to identify a nature of the symbol, and the processing of the graphical element is based on the nature of the symbol.

5. The system of claim 1, wherein the image processing subsystem is further configured to determine that the graphical element contains recognizable text and, responsive to an amount of the recognizable text exceeding a threshold, the image processing subsystem extracts the recognizable text from the graphical element and replaces the graphical element with the extracted text.

6. The system of claim 1, wherein image classification subsystem is further configured to classify a second graphical element as a dingbat and the weighting subsystem is further configured to apply a weighting of zero to the second graphical element responsive to the classification of the second graphical element as a dingbat.

7. The system of claim 6, wherein the classification of the second graphical element as a dingbat is based on at least one of:

a pixel area of the second graphical element;

repetition of the dingbat throughout the book;

a degree of complexity of the second graphical element; and

recognition of the second graphical element as a dingbat by an OCR engine.

8. A method of processing graphical elements within a book during assessment of the book for suitability for conversion to an audio format, the method comprising:

classifying a graphical element based on at least one of a context of the graphical element and properties of the graphical element;

processing the graphical element to create a processed graphical element, the processing responsive to the classification of the graphical element; and

producing a weighting corresponding to the processed graphical element, the weighting indicating an impact of the graphical element of suitability of the book for conversion to the audio format.

9. The method of claim 8, wherein the processing comprises, responsive to the classifying indicating the graphical element corresponds to text, replacing the graphical element with corresponding text.

10. The method of claim 9, wherein the corresponding text is based on the context of the graphical element.

11. The method of claim 8, wherein the graphical element is a symbol without a corresponding Unicode character, the method further comprises identifying a nature of the symbol, and the processing of the graphical element is based on the nature of the symbol.

12. The method of claim 8, wherein the processing comprises determining that the graphical element contains recognizable text and, responsive to an amount of the recognizable text exceeding a threshold, extracting the recognizable text from the graphical element and replacing the graphical element with the extracted text.

13. The method of claim 8, further comprising classifying a second graphical element as a dingbat and applying a weighting of zero to the second graphical element responsive to the classification of the second graphical element as a dingbat.

14. The method of claim 8, wherein the classification of the second graphical element as a dingbat is based on at least one of:

a pixel area of the second graphical element;

repetition of the dingbat throughout the book;

a degree of complexity of the second graphical element; and

recognition of the second graphical element as a dingbat by an OCR engine.

15. A non-transitory computer-readable medium storing instructions for processing graphical elements within a book during assessment of the book for suitability for conversion to an audio format, the instructions when executed by a computer processor cause the computer processor to:

classify a graphical element based on at least one of a context of the graphical element and properties of the graphical element;

process the graphical element to create a processed graphical element, the processing responsive to the classification of the graphical element; and

produce a weighting corresponding to the processed graphical element, the weighting indicating an impact of the graphical element of suitability of the book for conversion to the audio format.

16. The non-transitory computer-readable medium of claim 15, wherein the processing comprises, responsive to the classifying indicating the graphical element corresponds to text, replacing the graphical element with corresponding text.

17. The non-transitory computer-readable medium of claim 16, wherein the corresponding text is based on the context of the graphical element.

18. The non-transitory computer-readable medium of claim 15, wherein the graphical element is a symbol without a corresponding Unicode character, the instructions further cause the computer processor to identify a nature of the symbol, and the processing of the graphical element is based on the nature of the symbol.

19. The non-transitory computer-readable medium of claim 15, wherein the processing comprises determining that the graphical element contains recognizable text and, responsive to an amount of the recognizable text exceeding a threshold, extracting the recognizable text from the graphical element and replacing the graphical element with the extracted text.

20. The non-transitory computer-readable medium of claim 15, wherein the instructions further cause the computer processor to classify a second graphical element as a dingbat and apply a weighting of zero to the second graphical element responsive to the classification of the second graphical element as a dingbat.