船牌识别系统中的变形校正方法研究  

Study on Method of Distortion Correction in Ship License Plate Recognition System

作　　者：古辉[1] 王益义[1] 

机构地区：[1]浙江工业大学信息工程学院,浙江杭州310014

出　　处：《现代电子技术》2009年第10期87-90,共4页Modern Electronics Technique

基　　金：浙江省科技厅重大科技资助项目(2006C11202)

摘　　要：因摄像机角度而造成的图像倾斜和畸变,会给船牌的字符分割和识别带来不利影响。针对此问题,提出了一种新的变形校正方法。首先对定位后的船牌采用轮廓跟踪算法提取轮廓信息;然后采用一种基于Hough变换和K均值聚类直线拟合算法取得牌照的边框参数;最后通过双线性空间变换和灰度插值完成图像的校正。实验表明,这里提出的方法符合船牌图像的特点,具有较高的鲁棒性和工程实用性。Distortion ship license plate induced by camera location had the bad effect on its character segmentation and recognition. To solve this problem,a novel approach for distortion correction is presented in this paper. Firstly it uses the contour tracing algorithm to extract the edge of the license image after location. Then the parameters of four borders of the license plate are obtained by a method based on Hough transform and K--means--based line fitting algorithm is proposed. Finally image correction is realized in hilinear space transform and gray interpolation method. The experimental result shows that this method is effective to the image of ship license plate,and has good robustness and practicality.

关 键 词：变形校正 轮廓跟踪 HOUGH变换 双线性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]