作者：张博，杨维，耿放，马晓元，韩策策
单位：河北轨道运输职业技术学院，河北石家庄 052165
中图分类号：TP391                 
文献标识码：A                 
文章编号：1006-883X(2021)02-0017-06
收稿日期：2020-12-29

摘要：字符定位与识别技术在交通领域应用广泛。字符识别系统包括字符图像的拍摄、预先处理，将字符从图中截取出来，最后对字符对比甄别。采用灰阶处理、均值滤波等方法对图像预处理。在字符定位部分，采用边缘检测算法对字符图像在原始图中位置进行定位。在字符分割前，对字符进行二值化及倾斜校正。利用区域增长（region growing）方法切割字符，将具有相似特性的像素点集合到一起，与投影方法相结合进行切割。最后建立模板库，采用基于模板匹配的改进算法进行字符甄别。以汽车牌照的预处理、字符的提取和识别为例，说明文章所采用技术的有效性。
关键词：智能交通；图像处理；字符识别

Application of a Character Positioning and Recognition Technology in the Field of Transportation
ZHANG Bo, YANG Wei, GENG Fang, MA Xiaoyuan, HAN Cece   
Hebei Vocational College of Rail Transportation, Shijiazhuang 052165, China
Abstract: Character positioning and recognition technology is widely used in the transportation field. The character recognition system includes character image shooting, preprocessing, character extraction and recognition. Character image preprocessing is a key step in character positioning and recognition. In the paper, character images are preprocessed for grayscale, mean filter, median filter and other methods. The character positioning method of character image edge detection and mathematical morphology is realized, and the character area can be accurately extracted. In order to improve the effectiveness of character recognition, the characters need to be binarized and skew correction. Using the strategy of combining region growing and projection, the character segmentation is completed. Finally, a template library is established, and an improved algorithm based on template matching is used for character discrimination. Take the preprocessing of car license plate, character extraction and recognition as examples to illustrate the effectiveness of the technology used in the paper.
Key words: smart transportation; image processing; character recognition

阅读全文

备注：2021年 第27卷 第02期