摘要
基于CV(Chan-Vese)模型图像分割方法的不足,提出了一种改进的自适应图像分割方法,用于汽车车牌的字符识别.在这一方法中,为了避免初始位置差异对于分割效率的影响,设计了更为合理的分割流程.水平集合理论配合优化迭代算法,给出多个局部初值,大大增强了分割算法的自适应性能.实验结果表明,相比于CV模型图像分割方法,改进自适应图像分割方法的准确率更高,适用于汽车车牌图像的分割.
An improved adaptive image segmentation method based on CV model is proposed, which is ap-plied to the character recognition of vehicle license plate. In this method, in order to avoid the influence of the initial position difference on the segmentation efficiency, a more reasonable segmentation process is de-signed. The level set theory is combined with the optimal iterative algorithm, which gives a number of lo-cal initial values, which greatly enhances the performance of the segmentation algorithm. The experimen-tal results show that compared with the CV model image segmentation method, the improved adaptive im-age segmentation method is more accurate and suitable for the segmentation of vehicle license plate image.
出处
《西南师范大学学报(自然科学版)》
CAS
北大核心
2017年第5期28-33,共6页
Journal of Southwest China Normal University(Natural Science Edition)
基金
国家自然科学基金项目(61462008)
广西教育厅高校科研项目(LX2014187)
广西柳州市科学研究与技术开发计划项目(2016C050205)
关键词
汽车车牌
字符分割
模板匹配
自适应分割
vehicle l icense plate
character segmentat ion
template matching
adaptive segmentation