检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]东北师范大学人文学院信息技术学院,长春130117
出 处:《信息技术》2012年第10期53-57,共5页Information Technology
基 金:东北师范大学人文学院青年教师基金项目(2011007)
摘 要:车牌定位是车牌识别技术的第一步,车牌定位的准确与否直接影响着车牌识别的准确率。通过对现有的车牌定位方法进行研究,提出了一种复杂背景下的车牌定位算法,即利用车牌先验知识和灰度跳变结合来确定车牌位置,算法先对图像进行相应预处理,再结合纹理特征以及车牌区域的几何特征来粗定位车牌。粗定位时会得到对应的候选区域,如果候选区多于一个,就结合候选区的纹理特征和几何特征,利用算法来判断候选区是否是真实车牌区域;如果候选区只有一个,该候选区即是真实车牌,直接输出结果。实验结果表明,这种方法对复杂背景下的车牌定位比较准确,对噪音的抗干扰性强,定位速度快,符合实时性的要求。License plate location is the first step in license plate recognition technology,the license plate positioning accuracy directly affects the accuracy of license plate recognition.According to the study on the existing license plate location method,this paper presents a new method of license plate location in a complex context.To determine the license plate location by the use of license plate a prior knowledge and grayscale transitions combination.Based on the license area binarized texture characteristics of the internal as well as the geometric characteristics of the plate area to the coarse positioning license plate.Rough location,it can identify several candidate regions,if the number of candidate area is more than one candidate region,it have to collect the texture features and geometric features of the candidate region,using algorithms to determine whether the candidate region is a real license plate;if the candidate region is only one,then the candidate area is a real license plate,direct output.The experimental results show that this method is more accurate license plate location in the complex background with strongly noise interference,fast positioning speed.It's in keeping with the real-time requirements.
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.143