摘要
本文给出了一个能有效地分割/识别货车车号的方法。它已应用于实际系统并取得了满意的效果。算法包括三个部分:基于灰度梯度图像的图像分割,基于特定领域知识的图像分析和基于识别反馈的字符分割/识别,由于它们适应了实际问题的特点,本方法具有较好的鲁棒性。
This paper describes an effective method of segmenting and recognizing the characters on freight train automatically. This method has been used in practical system and obtained satisfying results. This algorithm consists of three components: image segmentation on gray-gradient, image, image analysis based on the domain knowledge and character segmentation/recognition based on recognition feedback. Tests of real application show that this method is robust.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
1998年第3期328-334,共7页
Pattern Recognition and Artificial Intelligence
关键词
图像分割
图文分离
字符识别
货运列车
车号
Image Segmentation. Figure-Text Separation, Character Recognition
