This paper proposes a new method for detecting a license plate and recognizing its numeric characters regardless of its image size. With this method, numeric characters on the license plate can be picked out using binarization with a feature that a contrast of the license plate is higher than the other part of the image. The numeric characters are detected and recognized using a neural network that has two functions; one judges whether each pattern is a numeric character or not, and the other recognizes what character it is. The license plate is detected using positions of the detected characters. To show the effectiveness of this method, experiments were performed. In these experiments using 126 pictures that were taken under various conditions, each numeric character recognition percent is 94.0 % and the license plate detection percent 97.6 %.
Dynamic detection of a license plate using neural network
Dynamische Erkennung eines Autokennzeichens mit Hilfe neuronaler Netze
2001
6 Seiten, 9 Bilder, 1 Tabelle, 10 Quellen
Article (Journal)
English
DYNAMIC LICENSE PLATE FOR DISPLAYING/OUTPUTTING LICENSE PLATE INFORMATION/DATA
European Patent Office | 2022
|LICENSE PLATE DETECTION DEVICE, COMPUTER PROGRAM AND LICENSE PLATE DETECTION METHOD
European Patent Office | 2015
|LICENSE PLATE SHEET, LICENSE PLATE LAMINATE, AND LICENSE PLATE
European Patent Office | 2019
|