| 摘要 |
PROBLEM TO BE SOLVED: To provide a license plate reader with improved accuracy of reading a license plate, even when the resolution of a character image is low or when characters are not clear, by reducing the influences thereof. SOLUTION: When a vehicle is detected, only high-resolution characters in a license plate are recognized from a frame image obtained from an imaging means. The time in which the vehicle travels from the time when the vehicle is detected until a distance between the license plate of the vehicle and the imaging means becomes a distance optimum for reading low-resolution characters in the license number is estimated on the basis of a vehicle speed detected by a vehicle speed detecting means. A plurality of frame images in the vicinity of the adjacent frames are extracted from frame images obtained from the imaging means when the estimated time elapses. The plurality of extracted frame images are used to increase the definition of a low-resolution character image in the license plate. Recognition processing is performed on only the low-resolution character image with high definition. The result of recognizing the low-resolution characters is combined with the result of recognizing the high-resolution characters. COPYRIGHT: (C)2011,JPO&INPIT
|
