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]华北电力大学控制科学与工程学院,保定071003
出 处:《仪器仪表用户》2008年第5期78-79,共2页Instrumentation
摘 要:汽车牌照定位是公认的较难解决的图像分割问题。本文基于HSI颜色模型给出了汽车牌照定位的新方法:首先对图像进行倾斜校正处理,然后将图像转换到HSI颜色空间,对该模型的H分量和S分量进行过滤获得二值化的汽车牌照图像,再通过孔洞检测去除未含有孔洞的连通域,并填充孔洞,运用数学形态学方法对二值图像处理,最后根据车牌照特征定位出车牌照区域。试验证明该方法达到了很好的定位效果。Vehicle license plate location is the image segmentation question which is recognized difficult to solve. Based on HSI color model, this article gives a new method to locate vehicle license plate: first, process tilt correction on the Image. Then transform the image to HSI color model space and carried filter on H and S compo- nents by which obtains the binary image. Eliminate connected do- mains which are not contain holes and fill holes by the holes detec- tion and apply mathematics morphology method on the binary ima- ger. Last, according to the characteristics of the license plate the plate region is located. The method had been approved achieving a good effect by experiments.
分 类 号:TP391.4[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:216.73.216.106