Method and system for character recognition

• US 8,620,083 B2
• Filed: 10/05/2011
• Issued: 12/31/2013
• Est. Priority Date: 12/03/2004
• Status: Active Grant

• Current Assignee: Kyocera Corporation
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: King, Martin T., Grover, Dale L., Kushler, Clifford A., Stafford-Fraser, James Q.
• Primary Examiner(s): Seth, Manav
• Application Number:
  US13/253,632
• Publication Number:
  US 20130243324A1
• Time in Patent Office: 818 Days
• Field of Search: None
• US Class Current: 382/181
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/93 Document management systems
• 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
• CPC Class Codes: G06V 30/153 using recognition of characters or words
• CPC Class Codes: G06V 30/158 using character size, text spacings or pitch estimation
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

Character recognition is described. In one embodiment, it may use matched sequences rather than character shape to determine a computer-legible result.

Claims

1. A non-transitory computer-readable medium with instructions encoded thereon, the instructions executable to cause one or more processors to perform operations comprising:

receiving an image including a plurality of characters;

dividing the image into a sequence of image segments, wherein individual image segments include one individual character of the plurality of characters;

comparing individual image segments to other image segments to identify similar characters;

assigning an identity symbol to each individual character of the plurality of characters, wherein the identified similar characters are assigned a common identity symbol; and

converting the sequence of image segments into a string of the assigned identity symbols.

2. The non-transitory computer-readable medium of claim 1, wherein:

a number of identity symbols represents the same number of different characters.

3. The non-transitory computer-readable medium of claim 1, wherein comparing individual image segments to the other image segments to identify similar characters comprises:

comparing individual pixels of the individual image segments to a correspondingly located pixel of an image segment of the other image segments;

determining a number of pixels of the individual image segment that are substantially identical to pixels of the image segment of the other image segments; and

determining that there is a match of characters between the individual image segment and the each image segment of the other image segments when a number of the remaining non-substantially identical pixels is less than or equal to a predetermined threshold of non-identical pixels.

4. The non-transitory computer-readable medium of claim 1,

wherein each assigned identity symbol represents a first location of the corresponding character of the image segments.

5. The non-transitory computer-readable medium of claim 1, wherein converting the sequence of image segments into a string of the assigned identity symbols comprises:

converting the sequence of image segments into a string of first location symbols.

7. The non-transitory computer-readable medium of claim 1, wherein the non-transitory computer-readable medium receives the image from an input device that creates the image.

8. The non-transitory computer-readable medium of claim 7, wherein the input device comprises at least one of an optical sensor and a linear array of optoelectronics.

9. The non-transitory computer-readable medium of claim 7, wherein the input device comprises a digital camera or a scanner.

10. The non-transitory computer-readable medium of claim 1, wherein the operations further comprise:

analyzing the received image to determine which parts of the image form a character.

11. The non-transitory computer-readable medium of claim 10, wherein analyzing the received image includes performing a white space analysis, a vector or blob analysis, or a width-based analysis.

12. The non-transitory computer-readable medium of claim 1,

wherein assigning an identity symbol to each individual character includes assigning a first identity symbol to a first character within a first image segment of the sequence of image segments, and

wherein assigning the first identity symbol to the first character within the first image segment occurs without comparing the first image segment to any other image segment of the sequence of image segments.

13. The non-transitory computer-readable medium of claim 12, wherein the operations further comprise:

storing, by the non-transitory computer-readable medium within cache, the first identify symbol with the first character and subsequently identifying the first identity symbol from cache if a subsequent character of the plurality of characters matches the first character.

14. The non-transitory computer-readable medium of claim 1, wherein the operations further comprise:

providing an indication that multiple results exist, wherein the multiple results include the string of the assigned identity symbols and another string of assigned identity symbols; and

receiving a selection of either the string of the assigned identity symbols or the another string of assigned identity symbols as a desired result.

15. The non-transitory computer-readable medium of claim 1, wherein the operations further comprise:

marking each unselected result of the multiple results for deletion from the non-transitory computer-readable medium.

6. A system for converting a character image into a string of symbols, the system comprising:

an optical image receiver programmed to receive an image including a plurality of characters;

one or more processors configured to;

(i) divide the image into a sequence of image segments, wherein each image segment of the sequence of image segments includes one individual character of the plurality of characters, (ii) compare each of the image segments to the other image segments to identify similar characters, (iii) to assign an identity symbol to each individual character of the plurality of characters, wherein the identified similar characters are assigned a common identity symbol, and (iv) convert the sequence of image segments into a string of the assigned identity symbols.

16. A method comprising:

receiving, by an optical image receiver, an image including a plurality of characters;

dividing, by one or more processors, the image into a sequence of image segments, wherein individual image segments include one individual character of the plurality of characters;

comparing, by the one or more processors, individual image segments to other image segments to identify similar characters;

assigning, by the one or more processors, an identity symbol to each individual character of the plurality of characters, wherein the identified similar characters are assigned a common identity symbol; and

converting, by the one or more processors, the sequence of image segments into a string of the assigned identity symbols.