Research And Realization Of License Plate Character Recognition Algorithm Based On SVM

Support Vector Machine(SVM)as an important theory of machine learning and patternrecognition has been well applied to small sample clustering learning, nonlinear problems, outlierdetection and so on. The License Plate Automation Recognition System has received extensiveattention as an important application of Machine Learning and Pattern Recognition in IntelligentTransport. Therefore, it is theoretically and practically significant to research the license platecharacter recognition technology based on SVM.The system is composed of three parts, license plate preprocessing and positioning, licenseplate character segment, license plate character recognition. In this thesis, with vehicle imagesobtained from the actual scene, a license plate recognition software was designed and realized.This research mainly consists of the following parts:1．In the part of preprocessing and position, The gray-scale, contrast enhancement, medianfiltering, canny edge detection, and threshold binarization method were applied in this research. Inthe positioning stage, the line scan mode and vertical projection means were used to effectivelydetermine the around borders for the followed character segment.2．In the part of the segment stage, the plates are detected and corrected with Houghtransform which can detect the tilt angle of the plate. With the inherent characteristics of thecharacter and geometry, the character segmentation boundaries are determined by the verticalprojection and threshold value. It overcome the shortcomings of the conglutination, fracture of thecharacter segmentation, effectively improve the accuracy of the character segmentation.3．In the part of character recognition, the features were extracted by normalized charactertrait. A method of SVM combined with Sequential Minimal Optimization algorithm was used forclassification and prediction, optimization parameter under small samples were obtained bycross-validation. A sample increasing experiment was made to show the optimal scale under theconditions of limited samples; for the recognition errors, an approach of supervised learning wasadopted. Recognition accuracy can be improved by re-learning train and joining the sampledatabase to build the modeling.4．Finally, a license plate recognition demonstration system software was developed utilizingthe existing laboratory resources and previous experiences, and the related interface functions and database design flow were illustrated.