| 一种基于小波变换的车牌字符识别算法 |
| |
| 引用本文： | 曲新亮 魏守水 杜洋. 一种基于小波变换的车牌字符识别算法[J]. 山东建筑工程学院学报, 2004, 19(3): 54-56 |
| |
| 作者姓名： | 曲新亮 魏守水 杜洋 |
| |
| 作者单位： | 山东大学控制科学与工程学院，山东大学控制科学与工程学院，山东大学控制科学与工程学院 山东济南250061，山东济南250061，山东济南250061 |
| |
| 摘 要： | 提出了一种小波变换的方法对提取出的车牌字符进行识别：对标准字符和分割好的车牌字符进行正交小波变换获取低频系数和高频系数，构造低频系数矢量和高频系数矢量，定义隶属函数，设定阈值，并定义加权矩阵。先将待辨识字符的低频系数矢量与标准字符的低频系数矢量相比较，再比较高频系数矢量。从而最终获得识别结果：实验结果证明该算法比常规识别算法识别率更高：
|
| 关 键 词： | 正交小波变换 Mallat算法 目标识别 |
A recognition algorithm for vehicle-license-plate characters based on wavelet transform |
| |
| QU Xin-liang,WEI Shou-shui,DU Yang. A recognition algorithm for vehicle-license-plate characters based on wavelet transform[J]. Journal of Shandong Institute of Architecture and Engineering, 2004, 19(3): 54-56 |
| |
| Authors: | QU Xin-liang WEI Shou-shui DU Yang |
| |
| Abstract: | A recognition algorithm for vehicle-license-plate characters has been presented based on wavelet transform. Orthogonal wavelet transform is carried out on the standard character images and the segmented character images to get the low and the high frequency coefficients respectively. From these coefficients ,vectors for the standard and the segmented images are constructed, and membership function is defined. After setting threshold value and weight matrix, the recognition results can be obtained by comparing the low and high frequency coefficients vectors of the recognizing characters with that of the standard characters. Experimental results testify the effectiveness of the algorithm. |
| |
| Keywords: | orthogonal wavelet transform Mallat algorithm pattern recognitions |
| 本文献已被 CNKI 维普 等数据库收录！ |
