四川大学学报（自然科学版）2018，Vol.55Issue(2)：290-294,5.DOI:10.3969/j.issn.0490-6756.2018.02.013
基于HSV和MB_LBP特征的级联Adaboost车牌检测算法
Detection algorithm of cascaded adaboost license plate based on HSV color model and MB_LBP features
摘要
Abstract
License plate detection is an important part of the license plate recognition system,w hich deeply affects the accuracy of license plate recognition.A method for cascade adaboost license plate de-tection based on HSV color model and multi-block local binary patterns(MB_LBP)is presented to real-ize fast and accurate license plate detection and recognition.Firstly,the license plate image is trans-formed from RGB color space to HSV color space,and the ratio of the blue pixels to the total pixels of the license plate is counted to construct the first class strong classifier.Then,the MB_LBP feature is extracted from the license plate character samples,and the feature selection and the classifier training are carried out by using the Adaboost classifier training method.Finally,a new license plate detection algo-rithm is formed by using the Cascade structure detection method.Experiments results show that the li-cense plate detector improves the detection rate and the detection speed.关键词
Adaboost算法/车牌检测/HSV颜色模型/MB_LBP特征/级联分类器Key words
Adaboost algorithm/Plate detection/HSV color model/MB_LBP features/Cascade classifier分类
信息技术与安全科学引用本文复制引用
马永杰,李欢,刘姣姣..基于HSV和MB_LBP特征的级联Adaboost车牌检测算法[J].四川大学学报（自然科学版）,2018,55(2):290-294,5.基金项目
国家自然科学基金(41461078) （41461078）
