Font reproduction in electronic documents
View Patent ↗A method, system, and computer program product for font reproduction in electronic documents are provided. The method includes: receiving an image of a printed document; extracting pairs of consecutive characters from the image of the printed document; storing the extracted pairs as images of the characters; and reproducing the printed document as an electronic document with text of overlapping extracted character pair images. Extracting pairs of consecutive characters includes extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters. Reproducing the printed document as an electronic document includes reproducing the spacing between words and between lines using the spaced horizontal characters and the spaced vertical characters as anchors in the reproduced document.
1. A method for font reproduction in electronic documents, comprising:
receiving an image of a printed document;
extracting pairs of consecutive characters from the image of the printed document;
storing the extracted pairs as images of the characters; and
reproducing the printed document as an electronic document with text of overlapping extracted character pair images;
wherein said steps are implemented in either:
computer hardware configured to perform said identifying, tracing, and providing steps, or
computer software embodied in a non-transitory, tangible, computer-readable storage medium.
2. The method as claimed in claim 1 , wherein extracting pairs of consecutive characters includes extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters.
3. The method as claimed in claim 2 , wherein reproducing the printed document as an electronic document includes reproducing the spacing between words using the spaced horizontal characters and between lines using the spaced vertical characters.
4. The method as claimed in claim 1 , including averaging the images in the form of bitmaps of the extracted pairs.
5. The method as claimed in claim 1 , wherein reproducing the printed document as an electronic document includes:
finding adjacent overlapping pairs;
adjusting the overlap by correlation of an overlapping character; and
blending the pairs.
6. The method as claimed in claim 1 , including storing all possible character pairs used in the printed document, wherein a character is a letter of an alphabet, a numeric character, or a punctuation character.
7. The method as claimed in claim 1 , including storing character pairs with a missing wildcard character for use when a character is missing.
8. The method as claimed in claim 1 , wherein reproducing the printed document as an electronic document includes:
compensating for a missing character by using a wildcard spacing and overlapping the wildcard with the consecutive character.
9. The method as claimed in claim 1 , including extrapolating character pairs to create missing character pairs.
10. The method as claimed in claim 1 , wherein the character pairs are extracted by an optical character recognition process with a confidence measure of a character recognition.
11. The method as claimed in claim 10 , wherein user input is made to confirm a character recognition.
12. The method as claimed in claim 1 , wherein extracting pairs of consecutive characters includes extracting sequences of more than two consecutive characters.
13. A method for font reproduction in electronic documents, comprising:
retrieving stored extracted pair images of consecutive characters from an image of a printed document; and
reproducing the printed document as an electronic document with text of overlapping extracted character pair images;
wherein said steps are implemented in either:
computer hardware configured to perform said identifying, tracing, and providing steps, or
computer software embodied in a non-transitory, tangible, computer-readable storage medium.
14. A computer program product for font reproduction in electronic documents, the computer program product comprising:
a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising: computer readable program code configured to:
receive an image of a printed document; extract pairs of consecutive characters from the image of the printed document; store the extracted pairs as images of the characters; and
reproduce the printed document as an electronic document with text of overlapping extracted character pair images.
15. A system for font reproduction in electronic documents, comprising:
a processor;
an extraction mechanism for extracting pairs of consecutive characters from an image of a printed document;
a pairs repository for storing the extracted pairs as images of the characters; and
an electronic document creator for reproducing the printed document as an electronic document with text of overlapping extracted character pair images.
16. The system as claimed in claim 15 , wherein the extraction mechanism extracts pairs of consecutive characters including extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters.
17. The system as claimed in claim 16 , wherein the electronic document creator includes a spacing module for reproducing the spacing between words and between lines using the spaced horizontal characters and the spaced vertical characters.
18. The system as claimed in claim 15 , wherein the extraction mechanism includes an averaging module for averaging the extracted images in the form of bitmaps.
19. The system as claimed in claim 15 , wherein the electronic document creator includes:
a finding module for finding adjacent overlapping pairs;
an adjustor for adjusting the overlap by correlation of an overlapping character; and
a blending module for blending the image pairs.
20. The system as claimed in claim 15 , wherein the electronic document creator includes a compensation module for generating a missing character by using a wildcard spacing in an image pair and overlapping the wildcard with a consecutive character.
21. The system as claimed in claim 15 , wherein the pairs repository includes a store of all possible character pairs used in the printed document, wherein a character is a letter of an alphabet, a numeric character, or a punctuation character.
22. The system as claimed in claim 15 , wherein the pairs repository includes a store of character pairs with a missing wildcard character for use when a character is missing.
23. The system as claimed in claim 15 , wherein the electronic document creator includes an extrapolator for extrapolating character pairs to create missing character pairs.
24. The system as claimed in claim 15 , wherein the extraction mechanism includes an optical character recognition system with a confidence measure of a character recognition.
25. The system as claimed in claim 24 , wherein the optical character recognition system includes a user interface for user input to confirm a character recognition.