Character recognition method and apparatus

• US 20030156755A1
• Filed: 10/17/2002
• Published: 08/21/2003
• Est. Priority Date: 02/20/2002
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Watanabe, Hiroshi, Tsunashima, Nobuhiro, Edanami, Takafumi, Momii, Akinori
• Granted Patent: US 7,103,199 B2
• Time in Patent Office: Days
• US Class Current: 382/182
• 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

Abstract

A character recognition method is provided, in which the method includes the steps of: picking up images in a motion picture by changing brightness for each image; extracting a character area from each image; recognizing at least one character in the character area by performing a matching process between the character area and dictionary images for each image, and determining a character recognition result for each image; and selecting a final character recognition result of which the matching degree is the highest from the character recognition results of the images. Accordingly, even when a character is too dark to recognize due to shadows in the daytime or a character is too bright to recognize due to irradiation in the nighttime, the character can be recognized by using images having differing brightness.

Claims

1. A character recognition method used for extracting a character area from a recognition target object in a motion picture and recognizing a character in said character area, said character recognition method comprising the steps of:

picking up images in the motion picture by changing brightness for each of the images;

extracting at least one character area from each image;

recognizing at least one character in said character area by performing a matching process between said character area and dictionary images for each image, and determining a character recognition result for each image; and

selecting a final character recognition result of which a matching degree is the highest from the character recognition results of said images.

2. A character recognition method used for extracting a character area from a recognition target object in a motion picture and recognizing a character in said character area, said character recognition method comprising the steps of:

extracting images having time difference with each other from the motion picture;

extracting said character area from each image;

recognizing at least one character in said character area by performing a matching process between said character area and dictionary images for each image, and determining a character recognition result for each image; and

selecting a final character recognition result of which a matching degree is the highest from the character recognition results of said images.

3. A character recognition method used for extracting a character area from a recognition target object in a motion picture and recognizing a character in said character area, said character recognition method comprising the steps of:

dividing an image in the motion picture into a plurality of regions including an upper region and a lower region;

extracting said character area from each region;

recognizing at least one character in said character area by performing a matching process between said character area and dictionary images for each region, and determining a character recognition result for each region;

selecting a final character recognition result of which a matching degree is the highest from the character recognition results of said regions; and

adjusting a focus of an image pickup apparatus to farther objects when said final character recognition is for said upper region, and adjusting said focus to nearer objects when said final character recognition is for said lower region.

4. A character recognition apparatus used for extracting a character area from a recognition target object in a motion picture and recognizing a character in said character area, said character recognition apparatus comprising:

a part for picking up images in the motion picture by changing brightness for each image;

a part for extracting said character area from each image;

a part for recognizing at least one character in said character area by performing a matching process between said character area and dictionary images for each image, and determining a character recognition result for each image; and

a part for selecting a final character recognition result of which a matching degree is the highest from the character recognition results of said images.

5. The character recognition apparatus as claimed in claim 4, said part for picking up images including a part for changing a shutter speed to change brightness for each image.

6. The character recognition apparatus as claimed in claim 4, said part for picking up images including a part for changing illumination to change brightness for each image.

7. A character recognition apparatus used for extracting a character area from a recognition target object in a motion picture and recognizing a character in said character area, said character recognition apparatus comprising:

a part for extracting images having time difference with each other from the motion picture;

a part for extracting said character area from each image;

a part for recognizing at least one character in said character area by performing a matching process between said character area and dictionary images for each image, and determining a character recognition result for each image; and

a part for selecting a final character recognition result of which a matching degree is the highest from the character recognition results of said images.

8. A character recognition apparatus used for extracting a character area from a recognition target object in a motion picture and recognizing a character in said character area, said character recognition apparatus comprising:

a part for dividing an image in the motion picture into a plurality of regions including an upper region and a lower region;

a part for extracting said character area from each region;

a part for recognizing at least one character in said character area by performing a matching process between said character area and dictionary images for each region, and determining a character recognition result for each region;

a part for selecting a final character recognition result of which a matching degree is the highest from the character recognition results of said regions; and

a part for adjusting a focus of an image pickup apparatus to farther objects when said final character recognition is for said upper region, and adjusting said focus to nearer objects when said final character recognition is for said lower region.