Apparatus and method for recognizing characters using a camera

• US 8,594,424 B2
• Filed: 12/07/2009
• Issued: 11/26/2013
• Est. Priority Date: 12/08/2008
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Hwang, Seong-Taek, Oh, Sang-Wook, Kim, Hyun-Soo, Kim, Sang-Ho, Kwon, Hee-Min, Oh, Yun-Je, Kim, Byung-Jik
• Primary Examiner(s): Seth, Manav
• Application Number:
  US12/632,118
• Publication Number:
  US 20100141788A1
• Time in Patent Office: 1,450 Days
• Field of Search: None
• US Class Current: 382/173
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: H04N 23/00 Cameras or camera modules comprising electronic image sensors; Control thereof

Abstract

An apparatus and method for recognizing characters of an image captured using a camera in a mobile terminal are provided, wherein an image of a signboard is captured, a text area is extracted from the captured image of the signboard, characters are recognized from the extracted text area, similar characters up to a predetermined priority level are generated for each recognized character of the extracted text area, location information of an area within a predetermined range from a current position of a user is acquired, store names are extracted from the location information, text is generated by combining the similar characters according to weights, the text are compared with the extracted store names, and a comparison result is output.

Claims

1. A method for recognizing characters of an image captured using a camera in a mobile terminal, comprising:

capturing, by the camera, an image of a signboard;

extracting a text area from the captured image of the signboard;

recognizing characters from the extracted text area;

generating similar characters of up to a predetermined priority level for each of the recognized characters of the extracted text area;

acquiring location information of an area within a predetermined range from a current position of the mobile terminal;

extracting at least one store name from the location information;

generating at least one text by combining the similar characters according to weights;

comparing the at least one text with the extracted at least one store name; and

outputting a comparison result.

2. The method of claim 1, wherein recognizing the characters from the extracted text area comprises:

converting the extracted text area to a binary black and white text area;

dividing the binary text area into the characters;

compensating for distortion of each of the characters; and

recognizing each of the compensated characters.

3. The method of claim 1, wherein generating the similar characters comprises generating similar results up to a predetermined priority level in a descending order of weights, for each of the characters.

4. The method of claim 1, further comprising:

classifying the at least one store name included in the location information, and storing the classified at least one store name in a database.

5. The method of claim 4, wherein storing the classified at least one store name comprises:

separating only store names having as many characters as the characters from the extracted text area; and

storing the separated store names.

6. The method of claim 1, wherein comparing the at least one text with the extracted at least one store name comprises:

comparing each of the at least one text with the extracted at least one store name, until a text matching any extracted store name is detected, and

wherein outputting the comparison result comprises;

outputting the text matching any extracted store name; and

outputting a text obtained by combining similar characters with highest weights on a character-by-character basis, if no text matches to any extracted store name.

7. The method of claim 1, wherein comparing the at least one text with the extracted at least one store name comprises:

identifying store names similar to the at least one text, and

wherein outputting the comparison result comprises;

outputting similar store names, for user selection.

8. The method of claim 7, wherein identifying the store names similar to the at least one text comprises:

comparing characters of the at least one text with characters of the extracted at least one store name; and

identifying store names that are identical to the at least one text in a predetermined number of characters.

9. The method of claim 1, wherein the current position of the mobile terminal is determined by a Global Positioning System (GPS).

10. The method of claim 1, wherein comparing the at least one text with the extracted at least one store name comprises:

comparing each character included in each of the at least one text with each character included in each of the at least one extracted store name in a predetermined order.

11. The method of claim 1, wherein comparing the at least one text with the extracted at least one store name comprises:

comparing a first character of each of the at least one text with a first character of each of the at least one extracted store name;

primarily re-classifying store names each having the first character identical to the first character of any of the at least one text;

comparing a second character of each of the re-classified store names with a second character of each of the at least one text;

secondarily re-classifying store names each having the second character identical to the second character of any of the at least one text among the re-classified store names; and

repeating the secondary re-classification, until comparison is completed over all characters included in the at least one text.

12. The method of claim 1, wherein comparing the at least one text with the extracted at least one store name comprises comparing each character included in each of the at least one text with each character included in each of the at least one extracted store name in a last-to-first character order.

13. An apparatus for recognizing characters from a captured image, comprising:

a capturer for capturing an image of a signboard and outputting the captured image;

a pre-processor for extracting a text area from the captured image and outputting the extracted text area;

a recognizer for recognizing characters from the extracted text area; and

a post-processor for generating at least one text by combining the recognized characters, comparing the at least one text with at least one store name within a predetermined range, and outputting a comparison result.

14. The apparatus of claim 13, wherein the at least one store name is received in location information of an area within the predetermined range from a current position of the apparatus.

15. The apparatus of claim 14, wherein the current position of the apparatus is determined by a Global Positioning System (GPS).

16. The apparatus of claim 13, wherein the pre-processor converts the extracted text area to a binary black and white text area, divides the binary text area into characters, and compensates for distortion of each of the characters, to facilitate recognition of the text.

17. The apparatus of claim 13, wherein the post-processor comprises:

a combination range setter for generating at least one similar character up to a predetermined priority level for each of the characters according to weights and storing the similar characters;

a character combiner for generating the at least one text by combining the at least one similar characters according to the weights;

a location information acquirer for acquiring the location information;

a database classifier for separating the at least one store name included in the location information and storing the at least one store name; and

a database comparator for comparing the at least one text with the at least one store name.