摘要
根据车牌图像具有不同颜色和车牌字符中字母和数字具有连通性的特点,提出将灰度自适应二值化和基于神经网络的彩色图像二值化相结合.用这种方法对一系列定位后的各种车牌图像进行二值化,然后利用投影法和数学形态学对二值化后的车牌进行准确的字符分割.实验结果表明:该方法二值化效果好,字符分割准确率较高.
According to the color features and the connectivity of characters in the vehicle license plate images, it is presented that the gray adaptive binarization is combined with the colorful image binarization based on neural network in this paper. A series of vehicle license plate images are binarized with this method after location, and the characters of the vehicle license plies are segmented accurately using the projection and mathematical morphology. The experiment results show that a good effect of binarization and a higher precision of character segmentation can be obtained through this approach.
出处
《湖南师范大学自然科学学报》
CAS
北大核心
2007年第4期60-64,共5页
Journal of Natural Science of Hunan Normal University
基金
湖南省自然科学基金资助项目(02JJY2059)
关键词
二值化
神经网络
数学形态学
字符分割
binarization
neural network
mathematical morphology
character segmentation
