摘要
研究车牌准确定位识别的问题,交通流量在高速条件下识别系统采集信息与数据有差异,同时在复杂背景中由于车牌的纹理区域面积太小造成车牌定位困难,传统的识别算法由于模板以及方向的选择困难,造成文字的识别率低的等问题。为解决上述问题,提出了一种利用数学形态学操作提取车牌和基于神经网络算法的车牌文字识别技术。首先将汽车图像进行边缘提取处理,提取候选区域,依据各个候选区域特性,进行形态学操作,从而可提取车牌图像,同时利用神经网络对车牌图像中的文字进行识别。实验结果显示改进的方法快速有效地提取车牌图像的边缘信息,所提取的车牌图像与真实车牌的位置吻合,提出的改进方法为车牌识别提供了参考。
Locating the car license plate in a car image is an important step in car license plate recognition/identification applications.This problem poses many challenges such as location of license plate from images taken in poor illumination and bad weather condition,recognition of plates partly obscured by dirt and images with low contrasts.This paper presented a morphology based method for license plate extraction from car images followed by the segmentation of characters and reorganization.This algorithm used morphological operations on the preprocessed edge images of the vehicles.Characteristic features such as license plate width and height,character height and spacing were considered for defining structural elements for morphological operations.The recognition of the contents of the License Plate was performed using cross correlation followed by neural network.The experimental results based on a reasonably large set of car images are very encouraging.
出处
《计算机仿真》
CSCD
北大核心
2011年第12期353-356,共4页
Computer Simulation
作者简介
廖春生（1967-），男（苗族），重庆秀山人，副教授，在读硕士，主要研究方向：计算机图形图像处理。
