Title :
Automatic system recognition of Lebanese license plates
Author :
Akoum, Al Hussain ; Daya, Bassam ; Chauvet, Pierre
Author_Institution :
Inst. of Appl. Math., UCO, Angers, France
Abstract :
License Plate Recognition is an image-processing technology that is used to identify vehicles by their Lebanese license plates. A license plate reader works by extracting the characters from an image. This technology is used for many applications such as toll booths, parking decks, border control, and law enforcement. As a solution to the problem of monitoring the tremendous number of vehicles for law enforcement and security, we use two methods of classifying the Lebanese plate in several areas: Labeling and K-Mean. Then, we have to extract from the plate the two classifications, which are the French line and the Arabic line. We separate each character from each line using the vertical profile method. Then we would recognize the characters by the algorithm of the K-PPV with a rate of recognition of the characters: The Arabic writing is of 82% and the Western writing is of 91 %. Finally we use a vote method between the two writings to increase the rate of recognition up to 93%.
Keywords :
character recognition; image classification; object recognition; vehicles; Arabic line; French line; Lebanese license plates; automatic system recognition; character extraction; image processing technology; k-mean classification; labeling classification; license plate recognition; vehicle identification; Image segmentation; character identification; fusion of basic algorithm; image processing; object detection; system recognition;
Conference_Titel :
Bio-Inspired Computing: Theories and Applications (BIC-TA), 2010 IEEE Fifth International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-6437-1
DOI :
10.1109/BICTA.2010.5645286