SYSTEM AND A METHOD FOR THE DETECTION OF MULTIPLE NUMBER-PLATES OF MOVING CARS IN A SERIES OF 2-D IMAGES

• US 20160314368A1
• Filed: 07/05/2016
• Published: 10/27/2016
• Est. Priority Date: 12/04/2013
• Status: Active Grant

• Current Assignee: Irida Labs S.A
• Original Assignee: Irida Labs S.A
• Inventors: Besiris, Dimitrios, Fragoulis, Nikos
• Granted Patent: US 9,547,800 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/56 having vectorial format
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names

Abstract

A stand-alone computer-camera system capable of extracting car-plate information. This is achieved by using an on-board computer in order to analyze the video stream recorded by the camera sensor, and can be used with any type of camera sensor. The system features specific characteristics making it extremely fast and able to catch plates of cars moving at high-speed. The special algorithms incorporated in this system, are specially implemented, in order to be able to be ported on an embedded computer system, which has usually lower capabilities in terms of processing power and memory than a general-purpose computer.

Claims

1-8. -8. (canceled)

9. A system comprising:

a storage system; and

a car-plate detection system that identifies car plates from one or more images captured by a camera, and utilizes region classification to determine whether a region within the one or more images is a car plate or is not a car plate, wherein the region classification is based upon pattern recognition using normalized central Hue moments determined in the run-length encoded domain where a feature vector comprised of each Hue moment is compared with a database of run-length encoded data corresponding to plates and run-length encoded data corresponding to nonplates.

10. The system of claim 9, wherein the comparison is performed using a projection.

11. The system of claim 9, further comprising a region classification unit that stores car plate coordinates in a detected plates coordinates memory.

12. The system of claim 9, further comprising a digit output unit that outputs digits of the car plate.

13. The system of claim 9, further comprising outputting digits of the car plate.

14. A method comprising:

receiving one or more images from a camera;

identifying car plates from the one or more images captured by the camera;

utilizing region classification to determine whether a region within the one or more images is a car plate or is not a car plate, wherein the region classification is based upon pattern recognition using normalized central Hue moments determined in the run-length encoded domain where a feature vector comprised of each Hue moment is compared with a database of run-length encoded data corresponding to plates and run-length encoded data corresponding to nonplates.

15. The method of claim 14, wherein the comparison is performed using a projection.

16. The method of claim 14, further comprising storing car plate coordinates in a detected plates coordinates memory.

17. The method of claim 14, further comprising outputting digits of the car plate.