Title :
An Algorithm Based on Geometric Region to Correct Tilt License Plates
Author :
Hong, Zhu Liang ; Feng, Liang Song
Author_Institution :
Shenzhen Polytech., Shenzhen, China
Abstract :
In the vehicle license plate recognition system(LPR), the license plate image would inevitably tilt to an extent. However, the tilt images will bring more difficult for further accurate segmentation and identification of characters, will eventually affect the recognition accuracy greatly. The traditional methods which based on Hough transform, in many situation, often can not accurately and promptly correct the plates, moreover, it needs a great amount of calculation, so the overall result is unsatisfactory. In this paper, Using a new algorithm based on geometric region, through rotating license plates, seeking for the minimum geometry region, then fast and accurate correction plates. The experimental results show that this method can detect the angle of tilt plates with simple calculation and high precision, which is better than the traditional algorithm based on Hough transform.
Keywords :
Hough transforms; computational geometry; image segmentation; object detection; object recognition; traffic engineering computing; Hough transform; LPR; character identification; character segmentation; license plate image; license plate rotation; minimum geometry region; tilt license plate correction; tilt plate angle detection; vehicle license plate recognition system; Accuracy; Character recognition; Geometry; Image segmentation; Licenses; Transforms; Vehicles; Coordinate rotation translation; Geometric region; Hough transform; Plates correction;
Conference_Titel :
Industrial Control and Electronics Engineering (ICICEE), 2012 International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-4673-1450-3
DOI :
10.1109/ICICEE.2012.180