Method and apparatus for formatting OCR text

• US 20020076111A1
• Filed: 12/18/2000
• Published: 06/20/2002
• Est. Priority Date: 12/18/2000
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Dance, Christopher R., Seeger, Mauritius
• Granted Patent: US 6,741,745 B2
• Time in Patent Office: Days
• US Class Current: 382/229
• CPC Class Codes: G06V 30/245 Font recognition

Abstract

Following scanning of a document image, and optical character recognition (OCR) processing, the outputted OCR text is processed to determine a text format (typeface and font size) to match the OCR text to the originally scanned image. The text format is identified by matching word sizes rather than individual character sizes. In particular, for each word and for each of a plurality of candidate typefaces, a scaling factor is calculated to match a typeface rendering of the word to the width of the word in the originally scanned image. After all of the scaling factors have been calculated, a cluster analysis is performed to identify close clusters of scaling factors for a typeface, indicative of a good typeface fit at a constant scaling factor (font size).

Claims

1. A method of determining a typeface for a plurality of words derived from a scanned image of text, the method comprising:

a) providing a plurality of candidate typefaces;

b) calculating for each typeface and for each word a scaling factor to match a typeface rendering of the word to the size of the word in the scanned image; and

c) analyzing the calculated scaling factors to identify a typeface which matches a plurality of the words.

2. A method according to claim 1, wherein the step of analyzing the scaling factors comprises identifying one or more clusters of the scaling factors indicative of a good fit of the typeface to a plurality of the words.

3. A method according to claim 1, wherein the scaling factor comprises a width component and a height component.

4. A method according to claim 1, wherein the size of the word in the scanned image is represented as a range of possible sizes between a minimum plausible size and a maximum plausible size.

5. A method according to claim 1, wherein the size of the word in the scanned image is represented as the dimensions of a bounding box around the word.

6. A method according to claim 1, further comprising the step of determining the size of each word in the scanned image.

7. A method according to claim 4, wherein the step of calculating a scaling factor comprises calculating a scaling factor range for fitting the typeface rendering of the word to said minimum and maximum plausible sizes of the word in the scanned image.

8. A method according to claim 1, wherein the step of analyzing the scaling factors comprises a first step of identifying for each typeface one or more optimum scaling factors which fit the largest number of words for that typeface.

9. A method according to claim 8, wherein the one or more optimum scaling factors form a range of optimum scaling factors.

10. A method according to claim 8, wherein the step of analyzing the scaling factors further comprises a second step of selecting the typeface having the largest number of words to which the optimum scaling factor fitted the typeface in the first step.

11. A method according to claim 10, further comprising allocating the selected typeface to the words to which the typeface fits with the optimum scaling factor, and repeating the first and second steps for other words to which no typeface has been allocated.

13. A computer program according to claim 12, wherein the step of analyzing comprises identifying one or more clusters of scaling factors for a typeface indicative of a good fit of the typeface to a plurality of the words.

15. A system according to claim 14, further comprising a typeface allocator for allocating a typeface to a word on the basis of the identified clusters.

16. A system according to claim 14, further comprising an optical character recognition processor for performing optical character recognition for deriving said words from the scanned image.

17. A system according to claim 14, further comprising a display generator for generating a display including the derived words rendered using the allocated typeface for each word.

18. A system according to claim 14, wherein the display generator is operative to generate a first display region including said words rendered using the allocated typeface, and a second region including a non-text region of the scanned image.

19. A system according to claim 18, further comprising a word based selection tool for enabling selection of one or more words from the first display region.

12. A computer program which when executed on a computer implements a method of determining a typeface for a plurality of words derived from a scanned image of text, the method comprising:

a) providing a plurality of candidate typefaces;

b) calculating for each typeface and for each word a scaling factor to match a typeface rendering of the word to the size of the word in the scanned image; and

c) analyzing the calculated scaling factors to identify a typeface which matches a plurality of the words.

14. A system for determining a typeface for a plurality of words derived from a scanned image of text, the system comprising:

a) an image analyzer for identifying the original size of each word in the scanned image;

b) a typeface processing device for calculating for each of a plurality of candidate typefaces and for each word, a scaling factor to match a typeface rendering of the word to said original size of the word in the scanned image; and

c) a cluster processor device for identifying one or more clusters of scaling factors for a typeface indicative of a good fit of the typeface to a plurality of the words.