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]华南理工大学机械与汽车工程学院,广州510640 [2]广州大学机械与电气工程学院,广州510006
出 处:《计算机应用研究》2014年第4期1236-1238,1251,共4页Application Research of Computers
基 金:机械系统与振动国家重点实验室开放课题资助项目(MSV-2013-11)
摘 要:针对现有形状匹配算法匹配速度慢、可靠性差的问题,提出了一种基于轮廓矢量化的形状匹配算法。将轮廓曲线点集离散化,使用多组向量对轮廓线性进行逼近。匹配时,结合线段在几何中的匹配方法,通过加权求和,计算源图像与目标图像中每组对应向量的相似度,将它们的平均值作为匹配结果。以焊盘表面轮廓为实验对象,使用所提出的算法进行匹配,结果表明,通过正确选取向量组数能有效避免匹配精度所受的影响,算法对不同类型的焊盘区分性较强,且匹配速度能满足实际应用的需要。To improve the calculation speed and reliability of the existing shape matching algorithm, this paper proposed a vector operation based contour-veetorization algorithm. It discretized the contour point set, and used several vectors to approach the contour curve linearly. In the matching, according to the geometric knowledge, calculated the similarity of each vector in the source image and the corresponding one in the target image through a weighted summation formula, calculated and the average of the similarities as their matching results. It used the pad surface contours as the experimental subjects, and the experimental results show that with the proposed algorithm the defect of matching accuracy can be effectively reduced by choosing the correct vector number, and differ- ent types of pads can be distinguished effectively while the matching speed can meet the needs of practical application.
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:216.73.216.28