Method and systems for processing text found in images

• US 8,644,546 B2
• Filed: 01/21/2010
• Issued: 02/04/2014
• Est. Priority Date: 09/26/2000
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Conwell, William Y.
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US12/691,608
• Publication Number:
  US 20110019869A1
• Time in Patent Office: 1,475 Days
• Field of Search: 382/100, 382/112, 382/306
• US Class Current: 382/100
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5846 using extracted text

Abstract

An image containing text (e.g., a surveillance camera photo that includes a vehicle license plate) is analyzed to determine the text (e.g., by an OCR technique). The recognized text is then stored in a database. The image is digitally watermarked with an identifier that associates the image with the database location where the text is stored. In addition to surveillance contexts, this technology can be employed in indexing the World Wide Web. Images used in web pages can be watermarked to link to associated text or other data. When the web page is crawled by an indexer, the watermark can be decoded and the associated data repository accessed to obtain information that can augment the web index for that page.

Claims

1. A method comprising:

receiving data corresponding to an image, wherein the image includes a depiction of text;

recognizing at least some of the depicted text; and

steganographically encoding a digital watermark in the image, wherein the steganographically encoded digital watermark associates the image with the recognized text, wherein the watermark comprises a visually imperceptible carrier of an identifier, and wherein the identifier comprises an index to a record of a database that includes additional information related to the image.

2. The method of claim 1, wherein recognizing at least some of the depicted text comprises recognizing at least some of the depicted text by an automated OCR process.

3. The method of claim 1, further comprising storing the recognized text in the database.

4. The method of claim 1, wherein the digital watermark directly encodes at least a portion of the recognized text in the image.

5. The method of claim 1, wherein encoding the digital watermark in the image occurs after recognizing at least some of the depicted text.

9. The method of claim 1, wherein the additional information related to the image comprises a keyword related to the image.

10. The method of claim 1, wherein the additional information related to the image comprises all of the depicted text.

11. The method of claim 1, wherein the additional information related to the image comprises full text of the depicted text.

6. A system comprising:

a scanner configured to produce scan data corresponding to an original document;

an OCR engine configured to recognize text from the scan data; and

a watermarker configured to alter the scan data to steganographically encode a digital watermark in the scan data, wherein the watermark associates the scan data with the recognized text, wherein the watermark comprises a visually imperceptible carrier of an identifier, and wherein the identifier comprises an index to a record of a database that includes additional information related to the scan data.

7. The system of claim 6, wherein the scan data represents a hardcopy page, and wherein the watermark further comprises a pointer to a memory location in which the recognized text is stored.

8. The system of claim 6, wherein the scan data represents a hardcopy page, and wherein the watermark directly encodes at least a portion of said recognized text in the scan data.

12. The system of claim 6, wherein the additional information related to the image comprises a keyword related to the image.

13. The system of claim 6, wherein the additional information related to the image comprises all of the depicted text.

14. The system of claim 6, further comprising the database that includes the additional information related to the scan data.

15. A non-transitory computer-readable medium having instructions stored thereon, that when executed by a computing device cause the computing device to perform operations comprising:

receiving data corresponding to an image, wherein the image includes a depiction of text;

recognizing at least some of the depicted text; and

steganographically encoding a digital watermark in the image, wherein the steganographically encoded digital watermark associates the image with the recognized text, wherein the watermark comprises a visually imperceptible carrier of an identifier, and wherein the identifier comprises an index to a record of a database that includes additional information related to the image.

16. The non-transitory computer-readable medium of claim 15, wherein recognizing at least some of the depicted text comprises recognizing at least some of the depicted text by an automated OCR process.

17. The non-transitory computer-readable medium of claim 15, wherein the digital watermark directly encodes at least a portion of the recognized text in the image.

18. The non-transitory computer-readable medium of claim 15, wherein the additional information related to the image comprises a keyword related to the image.