Image text replacement

• US 7,912,289 B2
• Filed: 05/01/2007
• Issued: 03/22/2011
• Est. Priority Date: 05/01/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zhao, Feng, Kansal, Aman
• Primary Examiner(s): Chawan; Sheela C
• Application Number:
  US11/743,048
• Publication Number:
  US 20080273796A1
• Time in Patent Office: 1,421 Days
• Field of Search: 382/181, 382/310, 382/229, 382/294, 715/205, 715/771, 715/277, 715/236, 715/234, 715/781, 715/788, 715/762, 715/763, 715/765, 348/E7.033, 358/1.18, 358/406, 358/452, 714/E11.171, 704/2, 704/251, 704/256.1, 704/256, 704/8
• US Class Current: 382/181
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• 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

Abstract

Image text enhancement techniques are described. In an implementation, graphically represented text included in an original image is converted into process capable text. The process capable text may be used to generate a text image which may replace the original text to enhance the image. In further implementations the process capable text may be translated from a first language to a second language for inclusion in the enhanced image.

Claims

1. A method comprising:

converting pixilated text, included in an original image, into process capable text that is stored in memory;

generating a text image of the process capable text, the text image being at least one of in a different font than the pixilated text, of a larger font than the pixilated text, or displayed in a different contrast than the pixilated text;

augmenting the original image using a processor with at least one of the text image or the process capable text to form an enhanced image.

2. The method as described in claim 1, further comprising translating the process capable text from at least one of a first human language into a second human language, such that the text image is in the second human language, or from a first human language into a symbol recognized by a culture employing the second human language.

3. The method as described in claim 2, wherein the at least one of the text image or the process capable text is inserted in the image in place of the graphic text.

4. The method as described in claim 3, wherein the text image is a bitmap of a symbol.

5. The method as described in claim 1, wherein the enhanced image is annotated with the process capable text.

6. The method as described in claim 1, wherein the enhanced image is annotated with at least one of a text balloon, an audio annotation, an image manipulation warning, or a highlighted portion.

7. The method as described in claim 1, wherein the enhanced image includes a process capable text overlay.

8. The method as described in claim 1, wherein process capable text is Unicode text.

9. One or more computer-readable memory comprising computer-executable instructions that, when executed by a processor, direct a computing system to:

optically recognize text included in a captured image as process capable text;

translate recognized process capable text from a first language into a second language;

output the captured image with a text image of the second language process capable text in place of the recognized text, the text image being at least one of a larger font than the recognized text, output in a higher contrast ratio than the recognized text, or output in a text balloon overlaid over the captured image.

10. The one or more computer-readable memory as described in claim 9, further comprising annotating the output image with the second language Unicode text.

11. The one or more computer-readable memory as described in claim 9, wherein the text image is a bitmap.

12. The one or more computer-readable memory as described in claim 9, wherein a natural language translation algorithm translates the first language Unicode text.

13. A system comprising:

an image capture device to obtain an image including original text that stores the original text in memory;

a text detection module to generate process capable text corresponding to the original text; and

an output module to output an enhanced image including the image with the original text replaced with a text image of the process capable text, the text image being at least one of a larger font than the original text, output in a higher contrast ratio than the original text, or output in a text balloon overlaid over the image.

14. The system as described in claim 13, further comprising a translation module to translate between process capable text in a first language into process capable text in a second language for output as the text image.

15. The system as described in claim 13, wherein the enhanced image is annotated with the Unicode text.

16. The system as described in claim 13, wherein the text detection module optically recognizes text within the image.

17. The system as described in claim 13, wherein system is included in at least one of a camera, a cellular phone, a smart phone, a video camera, a vehicle, or a wearable item.

18. The system as described in claim 13, wherein the text image is a bitmap.