Cyclic Mathematical Morphology in Polar-Logarithmic Representation

被引:10
作者
Angel Luengo-Oroz, Miguel [1 ]
Angulo, Jesus [2 ]
机构
[1] Univ Politecn Madrid, Biomed Image Technol Lab ETSI Telecomunicac, E-28040 Madrid, Spain
[2] Ecole Mines Paris, Ctr Math Morphol, F-77305 Fontainebleau, France
关键词
Circular opening; granulometric iris code; polar-logarithmic coordinates; radial skeleton; red blood cell shape analysis; spatially variant mathematical morphology; IRIS RECOGNITION; IMAGE;
D O I
10.1109/TIP.2009.2013078
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose in this paper to perform mathematical morphology operators in a geometric transformation of an image. As a result of this procedure, processing images with regular structuring elements in the transformed domain is equivalent to working with deformed structuring elements in the original representation. More specifically, the conversion into polar-logarithmic coordinates provides satisfying results in image analysis applied to round objects, if they are roughly origin-centered. We have illustrated the interest of the derived cyclic morphology with two pattern recognition examples: erythrocyte shape analysis and multiscale description of iris textures.
引用
收藏
页码:1090 / 1096
页数:7
相关论文
共 27 条