Zernike亚像素图像矩边缘检测算子方向角模型研究  

Research on sub-pixel Zernike moments edge detecting operator based on direction angle model

作　　者：姜迈[1] 梁炜[1] 张晓玲[1] 李世明[1] 

机构地区：[1]中国科学院沈阳自动化研究所工业控制网络与系统实验室,辽宁沈阳110016

出　　处：《传感器与微系统》2013年第2期16-19,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61174026);国家"863"计划资助项目(2011AA040101);国家"973"计划前期研究专项项目(2010CB334705);中国科学院知识创新工程重要方向性项目(KGCX2-EW-104-2)

摘　　要：基于Zernike图像矩的理想边缘模型,深入研究了方向角模型与亚像素判据间的关系。利用Zernike矩定义及其旋转不变特性,提出一种新的基于4阶方向角的Zernike矩亚像素边缘检测算子。为了提高边缘算子定位速度,首先基于9×9尺寸模板对Zernike图像矩0～4阶正交复数多项式进行了计算,推导出基于4阶方向角的边缘检测算子参数模型。最后将边缘算子应用在理想图像与实际图像上,检测结果表明:相比于传统的Zernike矩算子,基于4阶方向角的边缘检测算子具有更高的检测精度。Based on Zernike image moments edge model,relationship between direction angle model and sub-pixel criterion is studied deeply.A new edge detecting operator method based on 4-order direction angle is proposed,by using Zernike moments definition and its rotation invariance.In order to improve positioning speed of edge operator,the orthogonal complex polynomial is computed from 0 to 4 orders of the Zernike moments based on 9×9 mask,the edge detecting operator parameter model is deduced.Finally,edge operator is applied to ideal image and real image,test results show that the edge detecting operator based on 4-order direction angle has higher detecting precision compared with traditional method.

关 键 词：ZERNIKE矩 亚像素 正交复数多项式 4阶方向角 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]