IDENTIFICATION METHOD AND APPARATUS OF CONFUSABLE CHARACTER

• US 20130121581A1
• Filed: 12/27/2010
• Published: 05/16/2013
• Est. Priority Date: 07/20/2010
• Status: Active Grant

• Current Assignee: Hisense TransTech Co., Ltd. (Qingdao Huatong State-Owned Capital Operation (Group) Co., Ltd.)
• Original Assignee: Qingdao Hisense Transtech Company Limited
• Inventors: Liu, Wei, Wei, Nannan, Chen, Weiqiang, Liu, Xin, Pei, Lei, Wang, Xiaoman
• Granted Patent: US 9,008,430 B2
• Time in Patent Office: Days
• US Class Current: 382/182
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches

Abstract

An identification method and apparatus of confusable character are provided. The method involves: the detected character image is identified to gain the initial character information which is corresponding to the character image; the step change times of the corresponding external outline of the character image are counted if the initial character information is the confusable character; the final character information corresponding to the character image is confirmed according to the step change times; The final character information of the character image can be known conveniently according to the step change times, therefore the corresponding correct character information of the character image can be identified more precisely. The possibility of wrong identification of the character image because of the appearing confusable character can be reduced, and the identification precision rate of the confusable character can be improved.

Claims

1. A method for recognizing a confusable character, comprising:

recognizing a detected character image to obtain initial character information corresponding to the character image;

calculating the number of changes in gradient corresponding to the character image if the initial character information is a confusable character; and

determining final character information corresponding to the character image according to the number of changes in gradient.

2. The method for recognizing a confusable character according to claim 1, wherein before the calculating, the number of changes in gradient corresponding to the character image, the method further comprises:

setting a feature area corresponding to the character image according to a character shape in the initial character information it the initial character information is a confusable character; and

the calculating the number of changes in gradient corresponding to the character image further comprises calculating the number of changes in gradient corresponding to the feature area.

3. The method for recognizing a confusable character according to claim 2, wherein the calculating the number of changes in gradient corresponding to the feature area further comprises:

calculating the number of times that adjacent white pixel regions or adjacent black pixel regions among regions into which the feature area is divided are of different lengths as the number of changes in gradient corresponding to the feature area;

or

scanning the feature area per row, recording the locations of white-and-black transitions, and counting the number of times that the locations of white-and-black transitions are not in the same column across two adjacent rows as the number of changes in gradient corresponding to the feature area;

or

scanning the feature area per column, recording the locations of white-and-black transitions, and counting the number of times that the locations of white-and-black transitions are not in the same row across two adjacent columns as the number of changes in gradient corresponding to the feature area.

4. The method for recognizing a confusable character according to claim 2, wherein the feature area comprises an upper part and/or a lower part of the character image.

5. The method for recognizing a confusable character according to claim 4, wherein the feature area further comprises a central part of the character image.

6. The method for recognizing a confusable character according to claim 1, wherein the determining final character information corresponding to the character image according to the number of changes in gradient further comprises:

comparing the number of changes in gradient with a preset threshold to determine the final character information corresponding to the character image.

7. An apparatus for recognizing, a confusable character, comprising:

a recognizing module configured to recognize a detected character image to obtain initial character information corresponding to the character image;

a calculating module configured to calculate the number of changes in gradient corresponding to the character image if the initial character information is a confusable character; and

a determining module configured to determine final character information corresponding to the character image according to the number of changes in gradient.

8. The apparatus for recognizing a confusable character according to claim 7, further comprising:

a setting module configured to set a feature area corresponding to the character image according to a character shape in the initial character information if the initial character information is a confusable character; and

the calculating module is further configured to calculate the number of changes in gradient corresponding to the feature area.

9. The apparatus for recognizing a confusable character according to claim 8, wherein the calculating module comprises;

a determining sub-module configured to determine whether adjacent white pixel regions or adjacent black pixel regions in the feature area are of the same length; and

a calculating sub-module configured to increment the number of changes in gradient by one if the determining sub-module determines that adjacent white pixel regions or adjacent black pixel regions are of different lengths until the determination is made for all the pixel regions in the feature area.

10. The apparatus for recognizing a confusable character according to claim 7, wherein, the determining module is further configured to compare the number of changes in gradient with a preset threshold to determine the final character information corresponding to the character image.