Multiple image input for optical character recognition processing systems and methods

• US 7,734,092 B2
• Filed: 11/15/2006
• Issued: 06/08/2010
• Est. Priority Date: 03/07/2006
• Status: Active Grant

• Current Assignee: Ancestry.com Operations Inc. (Ancestry.com Incorporated)
• Original Assignee: Ancestry.com Operations Inc. (Ancestry.com Incorporated)
• Inventors: Reid, Shawn, Curtis, Donald B.
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Thomas; Mia M
• Application Number:
  US11/560,026
• Publication Number:
  US 20070211942A1
• Time in Patent Office: 1,301 Days
• Field of Search: 382173-178, 382/182, 358/462
• US Class Current: 382/182
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data

Abstract

A method of processing an image includes receiving a digital version of the image, processing the digital version of the image through at least two binarization processes to thereby create a first binarization and a second binarization, and processing the first binarization through a first optical character recognition process to thereby create a first OCR output file. Processing the first binarization through a first optical character recognition process includes compiling first metrics associated with the first OCR output file. The method also includes processing the second binarization through the first optical character recognition process to thereby create a second OCR output file. Processing the second binarization through the first optical character recognition process includes compiling second metrics associated with the second OCR output file. The method also includes using the metrics, at least in part, to select a final OCR output file from among the OCR output files.

Claims

1. A computer-readable medium having computer-executable instructions stored thereon for performing the computer-implementable method, the method comprising:

receiving a digital version of an image;

processing the digital version of the image through at least two binarization processes to thereby create a first binarization and a second binarization;

processing the first binarization through a first optical character recognition process to thereby create a first OCR output file, wherein processing the first binarization through a first optical character recognition process comprises compiling first metrics associated with the first OCR output file;

processing the second binarization through the first optical character recognition process to thereby create a second OCR output file, wherein processing the second binarization through the first optical character recognition process comprises;

compiling second metrics associated with the second OCR output file; and

using the first metrics and the second metrics, at least in part, to select a final OCR output file from among the OCR output files;

further comprising;

processing the first binarization through a second optical character recognition process to thereby create a third OCR output file, wherein processing the first binarization through a second optical character recognition process comprises compiling third metrics associated with the third OCR output file; and

processing the second binarization through the second optical character recognition process to thereby create a fourth OCR output file, wherein processing the second binarization through the second optical character recognition process comprises compiling fourth metrics associated with the fourth OCR output file.

2. The computer-implementable method of claim 1, wherein the binarization processes are selected from a group consisting of:

clustering;

global-thresholding; and

adaptive thresholding.

3. The computer-implementable method of claim 1, wherein the first and second optical character recognition processes comprise the same optical character recognition process.

4. The computer-implementable method of claim 1, wherein the first and second optical character recognition processes comprise different optical character recognition process.

5. The method of claim 1, wherein the first metrics and the second metrics comprise one or more selections from a group consisting of:

a number of characters recognized in the particular output file;

a number of dictionary words in the particular output file;

a number of unknown words in the particular output file;

a per-character confidence level in the particular output file;

a per-word confidence level in the particular output file;

a per-image confidence level in the particular output file;

a degree of agreement between the particular output file and other output files;

which binarization and OCR process produced the particular output file; and

a measure of historical accuracy associated with the particular binarization or OCR process combination that produced the particular output file.

6. The computer-implementable method of claim 1, further comprising creating the digital version of the image from a physical version of the image.

7. A method of optically recognizing characters in an image, comprising:

providing a computer system, wherein the computer system includes a computer readable medium, the computer readable medium having stored instructions for;

creating multiple binarizations of the image using different binarization techniques;

presenting each of the multiple binarizations to multiple optical character recognition (OCR) engines to produce multiple OCR output files for each binarization;

developing metrics relating to each OCR output file; and

using the metrics, at least in part, to select a final OCR output file from among the OCR output files;

wherein presenting each binarization to an OCR engine comprises presenting each binarization to a different OCR engine.

8. The method of claim 7, wherein the different binarization techniques comprise one or more selections from a group consisting of:

clustering;

global-thresholding; and

adaptive thresholding.

9. The method of claim 7, wherein the metrics relating to a particular OCR output file comprise one or more selections from a group consisting of:

a number of characters recognized in the particular OCR output file;

a number of dictionary words in the particular OCR output file;

a number of unknown words in the particular OCR output file;

a per-character confidence level in the particular output file;

a per-word confidence level in the particular output file;

a per-image confidence level in the particular output file;

a degree of agreement between the particular OCR output file and other OCR output files;

which binarization and OCR process produced the;

particular OCR output file; and

a measure of historical accuracy associated with the particular binarization or OCR combination that produced the particular OCR output file.

10. An optical character recognition system, comprising:

at least two binarization processes configured to convert a grayscale image to bitonal images;

at least two different optical character recognition processes configured to process at least, two bitonal images derived from—

the grayscale image into final output files having characters therein;

wherein presenting each binarization to an OCR engine comprises presenting each binarization to a different OCR engine;

further comprising a metrics generation process configured to analyze output files and produce metrics associated therewith;

a voting process configured to select a final output file from among the output files based on the metrics;

a storage arrangement configured to store final output files and serve the information therein to users and at least one processor programmed to execute the at least one optical character recognition processes, the at least one optical character recognition process, metrics generation process, and the voting process.

11. The optical character recognition system of claim 10, wherein the at least two binarization processes comprise at least one selection from a group consisting of:

clustering;

global-thresholding; and

adaptive thresholding.

12. The optical character recognition system of claim 10, wherein the metrics-associated with a particular output file comprise one or more selections from a group consisting of:

a number of characters recognized in the particular output file;

a number of dictionary words in the particular output file;

a number of unknown words in the particular output file;

a per-character confidence level in the particular output, file;

a per-word confidence level in the particular output file;

a per-image confidence level in the particular output file;

a degree of agreement between the particular output file and other output files;

which binarization and OCR process produced the particular output file; and

a measure of historical accuracy associated with the particular binarization or OCR combination that produced the particular output file.