包围圆分割在铁路货车车号字符的应用

针对铁路货车车号的断裂、倾斜、变形等特点,传统字符分割方法分割精度低的问题,提出一种基于改进包围圆的分割方法。基于铁路货车单行、双行2种排列方式,采用自适应游程算法进行双行车号的分割,鉴于游程算法背景像素前景化的处理特点,预先采用游程算法进行断裂消除,再使用包围圆方法进行字符分割。实验结果表明:在图像质量不高情况下,可以实现良好的分割精度且在分割准确率和鲁棒性方面均优于传统算法。

Application of enclosing circle segmentation in railway freight train number and characters

Due to the fracture, tilt, and deformation of railway freight train number and characters, the traditional segmentation method faces the problem of low segmentation accuracy. In this paper, a segmentation method based on improved enclosing circle was proposed. Firstly, the adaptive run length algorithm was used to segment the double line train number and characters based on the single line and double line arrangement of railway freight trains. With the characteristics of foreground processing of background pixels in run length algorithm, the run length algorithm was used to remove the breaks in advance, and then the enclosing circle method was used for character segmentation. The experimental results show that, in the case of low image quality, the proposed method can achieve good segmentation accuracy. Compared with the traditional algorithms, it is superior in segmentation accuracy and robustness.