CB形态金字塔及其在图像匹配中的应用  

CB morphological pyramid and its application for image matching

作　　者：杨刚[1] 亢洁[2] 

机构地区：[1]西安邮电学院通信与信息工程学院,西安710121 [2]陕西科技大学电气与信息工程学院,西安710021

出　　处：《信息技术》2011年第8期6-9,共4页Information Technology

摘　　要：提出了一种基于轮廓结构元素(CB)形态学的多尺度平形态开闭混合金字塔算法,该金字塔的图像分析算子为依次进行最大CB开滤波、最小CB闭滤波和上采样,而图像合成算子则直接采用下采样,这样使得该算法在分析时能较好保持图像的细节,且在合成时具有精确的信号重构能力。文中将其应用于图像匹配中作为搜索策略并进行了仿真实验,结果表明基于该算法的搜索策略可以使匹配速度有较大提高。A multiscale flat-structuring elements close-open hybrid pyramid algorithm based on contour-bougie（CB） morphology is presented.The image analysis operator of this pyramid consists of CB open-max filter,CB close-min filter and up-sampling in sequence,and the image synthesis operator uses down-sampling directly.Thus the algorithm can greatly preserve the image detail in analysis and has the perfect reconstruction capability in synthesis.It was applied as the search strategy for image matching in this paper and a simulation was performed.The results show that the search strategy based on this algorithm can highly raise the matching speed to be faster.

关 键 词：轮廓结构元素形态学 形态金字塔 多分辨率分析 图像匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]