摘要
针对道路场景中数字字符高噪声、多视角和难以定位识别的问题,提出了一种稳健的道路场景数字字符定位识别算法。采用基于色彩空间和边缘增强的最大稳定极值区域(MSER)算法来提取候选区域,设计了几何约束滤波器,并与笔画宽度变换(SWT)联合滤除非字符区域,得到字符定位结果。对Lenet-5中的收敛函数和池化窗进行改进,将定位后的字符区域归一化输入网络中,得到最终的字符识别结果。实验结果表明,本文算法的字符召回率达到90.0%,综合性能值达到0.89,字符识别率达到88.6%,优于同类算法性能。
To address the problems of large noise,multi-view,and difficult to locate and identify digital characters in road scenes,a robust method for recognizing digital characters in road scenes is proposed.According to this method,the maximally stable extremum region algorithm based on the color space and enhanced edge is used first to obtain candidate regions.Then,ageometrically constrained filter is designed and combined with the stroke width transform to filter non-character regions.The convergence function and pooling window of Lenet-5are improved,and the localized character regions are normalized and input into the network to obtain the final recognition results.According to the experimental results,the recall rate of the proposed method is 90.0%,the comprehensive performance value is 0.89,and the character recognition rate is 88.6%.These results are higher than those of the existing algorithms.
作者
白睿
徐友春
李永乐
李炯
谢枫
Bai Rui;Xu Youchun;Li Yongle;Li Jiong;Xie Feng(Army Military Transportation University,Tianjin300161,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2019年第19期203-211,共9页
Laser & Optoelectronics Progress
基金
国家自然科学基金(91220301)
国家重点基础研发计划(2016YFB0100903)
关键词
机器视觉
数字字符识别
色彩空间
最大稳定极值区域
笔画宽度变换
卷积神经网络
machine vision
digital character recognition
color space
maximally stable extremum region
stroke width transformation
convolution neural network
