IP Library Granted Patent US 8,059,868
Granted Patent B2
US 8,059,868 · App. 12/039,417 · Granted Nov 15, 2011

License plate recognition apparatus, license plate recognition method, and computer-readable storage medium

Assignee: Canon Kabushiki Kaisha
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,059,868
App. No.
12/039,417
Granted
Nov 15, 2011
Kind
B2
Abstract

A license plate recognition apparatus includes a detection unit configured to detect a plurality of quadrangles of license plate region candidates from input images, a character recognition unit configured to execute character recognition of a character region included in the license plate region candidate detected, and an output unit configured to select a license plate region candidate to be output from among the plurality of license plate candidates detected by the detection unit based on the character recognition result and information of the quadrangle of the respective license plate region candidates and output information relating to the license plate region candidates selected.

Claims (40)

1. A license plate recognition apparatus comprising:

a detection unit configured to detect a plurality of quadrangles of license plate region candidates from input images;

a character recognition unit configured to execute character recognition of a character region included in the detected license plate region candidates; and

an output unit configured to select a license plate region candidate to be output from among the plurality of license plate region candidates detected by the detection unit based on a character recognition result and the information of the quadrangle of the respective license plate region candidates and output information relating to the selected license plate region candidate,

wherein the output unit, in cases where positions of the license plate region candidates overlap, narrows the license plate region candidates to be selected by leaving the license plate region candidate whose angle of a quadrangle of the respective license plate region candidates is closer to a right angle, as the candidates.

2. The license plate recognition apparatus according to claim 1 , wherein the output unit, in cases where angles of the quadrangles of the respective license plate region candidates are identical, narrows the license plate region candidates to be selected based on areas of the respective quadrangles.

3. The license plate recognition apparatus according to claim 1 , wherein the output unit performs narrowing down processing of the license plate region candidates whose character recognition results are identical and whose positions overlap and then performs the narrowing down processing of the license plate region candidates whose character recognition results are different and whose positions overlap.

4. The license plate recognition apparatus according to claim 1 , wherein the output unit narrows down the license plate region candidate to be selected based on the character recognition result of the license plate region candidate and the position of the character region included in the license plate region candidate.

5. The license plate recognition apparatus according to claim 1 , wherein the output unit, in cases where there are the plurality of license plate region candidates, selects the license plate region candidates to be output after sorting the license plate region candidates based on a size order of an area of the license plate region candidate or an order of a position close to a center of the input images, and outputs information relating to the selected license plate region candidate.

6. The license plate recognition apparatus according to claim 1 , wherein the detection unit detects the quadrangle of the license plate region candidate by detecting connected pixel rows arranged in a straight line shape from the input images, setting a processing object range based on the connected pixel rows detected, and executing processing to detect the quadrangle in the processing object range set.

7. A method for causing a license plate recognition apparatus to execute operations in such a way that a computer of the license plate recognition apparatus executes a computer program, the operations comprising:

detecting a plurality of quadrangles of license plate region candidates from input images;

executing character recognition of a character region included in the license plate region candidates detected; and

selecting a license plate region candidate to be output from among the plurality of license plate region candidates detected based on a character recognition result and information of the quadrangle of the respective license plate region candidates and outputting information relating to the selected license plate region candidates,

wherein in cases where positions of the license plate region candidates overlap, narrows the license plate region candidates to be selected by leaving the license plate region candidate whose angle of a quadrangle of the respective license plate region candidates is closer to a right angle, as the candidates.

8. A non-transitory computer readable storage medium storing a computer program, in which the computer program causes a computer to execute operations comprising:

detecting a plurality of quadrangles of license plate region candidates from input images;

executing character recognition of a character region included in the license plate region candidates detected; and

selecting a license plate region candidate to be output from among the plurality of license plate region candidates detected based on character recognition result and information of the quadrangle of the respective license plate region candidates and outputting information relating to the selected license plate region candidates,

wherein in cases where positions of the license plate region candidates overlap, narrows the license plate region candidates to be selected by leaving the license plate region candidate whose angle of a quadrangle of the respective license plate region candidates is closer to a right angle, as the candidates.

9. The computer readable storage medium according to claim 8 , the operations further comprising:

narrowing the license plate region candidates to be selected based on areas of the respective quadrangles, in cases where angles of the quadrangles of the respective license plate region candidates are identical.

10. The computer readable storage medium according to claim 8 , the operations further comprising:

performing narrowing down processing of the license plate region candidates whose character recognition results are identical and whose positions overlap and then performing narrowing down processing of the license plate region candidates whose character recognition results are different and whose positions overlap.

11. The computer readable storage medium according to claim 8 , the operations further comprising:

narrowing down the license plate region candidates to be selected based on the character recognition result of the license plate region candidates and the position of the character region included in the license plate region candidates.

12. The computer readable storage medium according to claim 8 , the operations further comprising:

selecting the license plate region candidates to be output after sorting the license plate region candidates based on a size order of an area of the license plate region candidates or an order of a position of the license plate region candidates existing close to a center of the input images, and outputting information relating to the license plate region candidate selected, in cases where there are the plurality of license plate region candidates.

13. The computer readable storage medium according to claim 8 , the operations further comprising:

detecting the quadrangle of the license plate region candidates by detecting a connected pixel row arranged in a straight line shape from the input images, setting a processing object range based on the connected pixel row detected, and executing processing to detect the quadrangle in the processing object region set.

14. The method according to claim 7 , the operations further comprising:

narrowing the license plate region candidates to be selected based on areas of the respective quadrangles, in cases where angles of the quadrangles of the respective license plate region candidates are identical.

15. The method according to claim 7 , the operations further comprising:

performing narrowing down processing of the license plate region candidates whose character recognition results are identical and whose positions overlap and then performing narrowing down processing of the license plate region candidates whose character recognition results are different and whose positions overlap.

16. The method according to claim 7 , the operations further comprising:

narrowing down the license plate region candidates to be selected based on the character recognition result of the license plate region candidates and the position of the character region included in the license plate region candidates.

17. The method according to claim 7 , the operations further comprising:

selecting the license plate region candidates to be output after sorting the license plate region candidates based on a size order of an area of the license plate region candidates or an order of a position of the license plate region candidates existing close to a center of the input images, and outputting information relating to the license plate region candidate selected, in cases where there are the plurality of license plate region candidates.

18. The method according to claim 7 , the operations further comprising:

detecting the quadrangle of the license plate region candidates by detecting a connected pixel row arranged in a straight line shape from the input images, setting a processing object range based on the connected pixel row detected, and executing processing to detect the quadrangle in the processing object region set.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 18, 2008
From: MATSUMOTO, HIDEAKI; UMEDA, ICHIRO
To: CANON KABUSHIKI KAISHA
Reel/Frame 020663/0155 →
Priority Claims (1)
JP 2007-053049 · Mar 2, 2007 · national
Continuity (1)
Related Publication 20080212837A1 · Sep 4, 2008