计算机工程
計算機工程
계산궤공정
COMPUTER ENGINEERING
2010年
3期
192-194
,共3页
车牌定位%字符识别%特征提取%倾斜校正
車牌定位%字符識彆%特徵提取%傾斜校正
차패정위%자부식별%특정제취%경사교정
location of license plate%character recognition%feature extraction%tilt correction
提取车牌字符的Haar特征作为输入,通过级联的神经网络分类器对其进行识别,以定位车牌字符的位置,并根据所得车牌字符位置的相对关系确定车牌位置.该方法不需要进行倾斜矫正,减少了车牌定位后进行字符分割时的工作量.实验结果表明,该方法能准确快速地定位并分割车牌.
提取車牌字符的Haar特徵作為輸入,通過級聯的神經網絡分類器對其進行識彆,以定位車牌字符的位置,併根據所得車牌字符位置的相對關繫確定車牌位置.該方法不需要進行傾斜矯正,減少瞭車牌定位後進行字符分割時的工作量.實驗結果錶明,該方法能準確快速地定位併分割車牌.
제취차패자부적Haar특정작위수입,통과급련적신경망락분류기대기진행식별,이정위차패자부적위치,병근거소득차패자부위치적상대관계학정차패위치.해방법불수요진행경사교정,감소료차패정위후진행자부분할시적공작량.실험결과표명,해방법능준학쾌속지정위병분할차패.
This paper extracts the Haar features of license plate characters as input and identifies the input by a cascaded neural network classifier to locate the position oflicense plate characters.It locates the license plate position according to the relative relationship of the obtained license plate characters.This method does not require tilt correction and reduces the work of character segmentation after location of license plate.Experimental results show that the method can locate and divide the plate quickly and accurately.
