摘要
在移动式拍摄环境下进行车牌字符自动识别受到模糊干扰以及环境的因素影响,导致车牌字符自动识别的准确性不好,提出一种基于机器视觉的车牌字符自动识别系统设计方法。将车辆环境信息融入到车牌字符图像的边缘轮廓检测中,提取车牌字符关键信息特征点,把车牌字符的内部结构纹理信息解释为一个灰度直方图均匀分布的随机场,进行车牌字符图像的灰度特征检测和字符块匹配处理,在不同的车辆行驶速度下选用不同的特征匹配函数来统计车牌字符的机器视觉特征分布点,进行车牌字符的目标像素视差分析和视觉特征检测。在Android开发环境下进行车牌字符自动识别系统的软件开发设计。仿真结果表明,采用该方法进行车牌字符自动识别具有准确识别率高、捕获性能好、识别用时短的优点。
The automatic recognition of license plate characters in mobile shooting environment is affected by ambiguity and environmental factors,which leads to the inaccuracy of the automatic recognition of license plate characters.A design method of automatic recognition system of license plate characters based on machine vision is proposed.The vehicle environment information is integrated into the edge contour detection of the license plate character image,the key information feature points of the license plate character are extracted,and the texture information of the internal structure of the license plate character is interpreted as a random field with uniform distribution of gray histogram.The gray level feature detection and character block matching of license plate character image are carried out,and different feature matching functions are selected under different vehicle driving speed to calculate the distribution points of license plate characters’machine vision features.The target pixel parallax analysis and visual feature detection of license plate characters are carried out.The software development and design of the license plate character recognition system is carried out in the environment of Android.The simulation results show that this method has the advantages of high accurate recognition rate,good acquisition performance and short recognition time.
作者
魏娇
WEI Jiao(Xianyang Vocational Technical College,Shanxi Xianyang 712000,China)
出处
《自动化与仪器仪表》
2019年第8期49-53,共5页
Automation & Instrumentation
基金
咸阳职业技术学院科研基金项目(No.2018KYB03)
关键词
ANDROID
机器视觉
车牌字符
自动识别系统
Android
machine vision
license plate characters
automatic recognition system
