LULU Operators and Discrete Pulse Transform for Multidimensional Arrays

被引:10
|
作者
Anguelov, Roumen [1 ]
Fabris-Rotelli, Inger [1 ]
机构
[1] Univ Pretoria, Dept Math & Appl Math, ZA-0083 Pretoria, South Africa
关键词
Area closing; area opening; connection; discrete pulse transform (DPT); LULU; separator; total variation; LOCALLY MONOTONIC REGRESSION; IDEMPOTENT STACK FILTERS; BOUNDED VARIATION; SMOOTHERS; DECOMPOSITION; SEGMENTATION; IMAGES;
D O I
10.1109/TIP.2010.2050639
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The LULU operators for sequences, that is L(n), U(n) and their compositions, are extended to multidimensional arrays in a way which preserves their essential properties, e. g., consistent separation, total variation and shape preservation. The power of the operators is demonstrated by deriving the discrete pulse transform (DPT), which is a hierarchical decomposition of the input array into pulses. Similar to its 1-D counterpart this transform satisfies a basic consistency property.
引用
收藏
页码:3012 / 3023
页数:12
相关论文
共 50 条