《Saudi License Plate Recognition Algorithm Based on Support Vector Machine》由会员分享，可在线阅读，更多相关《Saudi License Plate Recognition Algorithm Based on Support Vector Machine（5页珍藏版）》请在金锄头文库上搜索。
1、424 JOURNALOFELECTRONIC SCIENCEANDTECHNOLOG VOL11，NO4，DECEMBER 2013 Saudi License Plate Recognition Algorithm Based on Support Vector Machine Khaled Suwais，Rana A1一Otaibi，and A1i Alshahrani Abstrac icense plate recognition(LPR)is an image processing technology that is used to identify vehicles by th
2、eir license platesThis paper presents a license plate recognition algorithm for Saudi car plates based on the support vector machine(SVM)algorithm The new algorithm is efficient in recognizing the vehicles from the Arabic part of the plateThe performance of the system has been investigated and analy
3、zedThe recognition accuracy of the algorithm is about 933 ndex Terms-Image processing，license plates recognition systems，support vector machine 1 Intr0ducti0n The principles of image processing are originally derived from different disciplines，sciences，and fields including mathematics，computer scien
4、ce，optics，visual psychophysics，and surface physics【IJ_Processing of digital images can be made by various methodshowever,there are three main operations that are commonly used to completely comprehend the meaning of an image：filtration or restoration， enhancement， and understanding In ltrationrestor
5、ation and enhancement operationsthe aim is to clarify an images meaning through working on a corrupt image and trying to identically recover the original image that could be easily recognized by humansThe license plate recognition(LPR)uses the combination of methods to catch the license plate number
6、 of any moving vehicle This system is composed of a camera to take an image， illumination for clarificationand a suite of algorithms Algorithms and illuminations have the main function of Manuscript received March 820l3：revised July 8，20l3 KSuwais is with the Faculty of Computer StudiesArab Open Uni
7、versity，Riyadh l 1861，Saudi Arabia(Corresponding author e-mail： khaledsuwaisarabouedusa) AAlshahrani is witll the Faculty of Computer StudiesArab Open University，Riyadh l1861，Saudi Arabia(email：ashahraniarabou edusa) RAIOtaibi is with the Computer and Electronics Research Institute King Abdulaziz Ci
8、ty for Science and Technology，Riyadh l 1442，Saudi Arabia femail：ralotaibikacstedusa) Color versions of one or more of the figures in this PaDer are available online athttO：wwwint1jestcom Digital Object Identifier：103969jissn1674862X_20l3040l6 giving a meaning for the image that can be identified and
9、 recognized by human visual mechanismsThis system is very helpfu1 and is regarded as one of the most intelligent systems for transportation since it can be applied in many areas that require monitoringsuch as toll collection and tra伍CThe importance and usefulness of LPR have increased due to the rap
10、id growth of vehicles in every city around the worldFor a big city like Riyadhthe implementation of LPR has become very significant in order to monitor the movement of vehicles through identifying their license plate numbersThis technology of image processing has four major stepsThe first is acquiri
11、ng an image of the license plate；the second is to extract the license plate；the third step iS making segmentation of the plate； and the fourth is the reorganization of the license plateTechnologies of LPR are helpfu1 applications in traf矗e systems which include traf玎c movements，parking lots，and acce
12、ss contro1 Arab countries use license plates that hold the name of the country or an abbreviation indicating the countrys name in Arabic or English lettersIn additionthe plate also contains both Arabic and English letters and numerals to indicate the vehicles license numberHereour foCUS iS given to
13、the recognition of the Arabic letters and numerals contained in the new license plate used in Saudi Arabia(see Fig1、A new algorism will be implemented so that captured images can be processed immediately 2Literature Review Invention of automatic recognition of number plates took place in l976 and it
14、 was used for the first time as a working application in the UK in l 969This new technology attracted many researchers to investigate and develop their techniques and mechanisms for recognizing vehicles license plates through image processingThe four major steps that compose the LPR system are inves
15、tigated and discussed through different methodologies that yielded various important conclusions Fig1NewSaudilicenseplate SUWAIS et a1：Saudi License Plate Recognition Algorithm Based on Support Vector Machine 425 In the study conducted by E1 Adawi license plate(LP) extraction was carried out by conv
16、erting the RGB(red， greenblue)image to a grayscale oneThe data amount in the image was decreased and the unwanted data was avoided by using the corresponding algorithmThe area that shared the similar properties with the license plate was extractedSpatia1 filtering was employed to make the images edges detectable：horizontal and vertical directions were detected by using the convolution kerne1The foll
