Character segmentation method and apparatus

• US 7,302,098 B2
• Filed: 12/03/2004
• Issued: 11/27/2007
• Est. Priority Date: 12/03/2004
• Status: Active Grant

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Tang, Bei, Lee, King F.
• Primary Examiner(s): Tran; Phuoc
• Application Number:
  US11/004,738
• Publication Number:
  US 20060120602A1
• Time in Patent Office: 1,089 Days
• Field of Search: 382/174, 382/177, 382/200, 382/266, 382/237
• US Class Current: 382/177
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images

Abstract

An electronic device (1100) and a method for character segmentation (100) includes an image analyzer (1110) that generates individual character images. The image analyzer binarizes (115) a gray scale image (200) of a horizontal row of characters by using a general threshold method to generate a first image (300). The image analyzer also binarizes (120) the gray scale image using an edge detection method to generate a second image (405). The image analyzer determines (125) a character row region (425) of the second image by using horizontal projection analysis. The image analyzer isolates (130) the character row region of the first image using the character row region of the second image. The image analyzer uses the character row region to generate (135) individual character images. The electronic device may include an image capture device (1105) and a character recognition program (1115).

Claims

1. A method of character segmentation for character recognition, comprising:

first binarizing a gray scale image using a general threshold method to generate a first image;

second binarizing the gray scale image using an edge detection method to generate a second image;

determining a character row region of the second image by using horizontal projection analysis;

generating an isolated character row image of the first image using the character row region of the second image; and

generating individual character images from the isolated character row image.

2. The method according to claim 1, wherein generating individual character images is accomplished by using vertical projection analysis of the isolated character row image.

3. The method according to claim 1, wherein generating individual character images is accomplished by using connected component analysis of the isolated character row image.

4. The method according to claim 1, further comprising performing character recognition of each of the individual character images.

5. The method according to claim 1, wherein determining a character row region of the second image further comprises:

generating a horizontal projection of the second image comprising counts of edge pixels in each row of the second image;

determining a horizontal projection threshold by analyzing the horizontal projection of the second image;

determining boundaries of the character row region by using the horizontal projection threshold and the horizontal projection to define a character row region mask.

6. The method according to claim 1, further comprising:

capturing an image; and

generating a gray scale image having at least one horizontal row of characters comprising the individual character images.

7. A means for performing character segmentation for character recognition, comprising:

first means for binarizing a gray scale image using a general threshold method to generate a first image;

second means for binarizing the gray scale image using an edge detection method to generate a second image;

means for determining a character row region of the second image by using horizontal projection analysis;

means for isolating the character row region of the first image using the character row region of the second image; and

means for using the isolated character row region to generate individual character images.

8. An electronic device, comprising:

image capture means that generate a gray scale image that includes a horizontal row of characters;

image analyzer means that generate individual character images, comprising

first means for binarizing a gray scale image of the horizontal row of characters by using a general threshold method to generate a first image,

second means for binarizing the gray scale image using an edge detection method to generate a second image,

means for determining a character row region of the second image by using horizontal projection analysis,

means for isolating the character row region of the first image by using the character row region of the second image, and

means for using the isolated character row region to generate individual character images; and

character recognition means for recognizing the individual character images.