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]浙江大学CAD&CG国家重点实验室,浙江杭州310027
出 处:《浙江大学学报(工学版)》2011年第6期1013-1020,共8页Journal of Zhejiang University:Engineering Science
基 金:教育部博士点基金资助项目(200803350031);浙江省自然科学基金重点资助项目(Z1080339)
摘 要:为了通过对制件图像进行轮廓匹配实现外形异常识别,提高生产效率和产品质量,提出制件外形多分辨轮廓匹配检测技术,通过分析起点对轮廓曲线的各分辨率小波变换的影响,建立轮廓某尺度下小波逼近量的搜索匹配策略,实现粗匹配下的形变判定.研究匹配轮廓段局部特征以及轮廓区间对的相异度统计,进而获得轮廓点对的精确对准,达到轮廓精配准,实现飞边、缺损等缺陷类型判定,最终得出外形检测结果.该方法在多种制件图像、各种外形异常类型中进行应用验证,结果表明外形检测准确度满足要求.A method of shape detection was proposed to match the shape of products to achieve anomaly recognition,thereby improve the production efficiency and products quality.The affection of starting point to the multi-resolution wavelet transformation was studied,and a searching and matching strategy of the wavelet approximation at an certain scale was established to achieve rough matching.Then,the local features of contour segments and the dissimilarity statistics of pairs of contours were used to achieve the precise matching of contour detects,and then realize the judgment of types of defects such as flash and short shot.The final detection result was obtained through previous two steps.The method was verified by the experiments including several kinds of products and different shape anomalies.
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术] TN911.73[自动化与计算机技术—计算机科学与技术]
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:216.73.216.222