基于信号稀疏表示的形态成分分析:进展和展望  

Advances and Perspective on Morphological Component Analysis Based on Sparse Representation

作　　者：李映[1] 张艳宁[1] 许星[1] 

机构地区：[1]西北工业大学计算机学院,陕西西安710072

出　　处：《电子学报》2009年第1期146-152,共7页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60873086);博士点基金(No.20070699013);陕西省自然科学基础研究计划(No.2006F05);航空科学基金(No.05I53076)

摘　　要：有效的信号和图像分解(分离)技术在信号和图像的分析、增强、压缩、复原等领域起着重要的作用.虽然目前研究者提出了很多方法来解决这个问题,然而处理效果并不完美.形态成分分析(Morphological Component Analy-sis,MCA)是最新提出的一种基于稀疏表示的信号和图像分解(分离)方法.该方法的主要思想是利用信号组成成分的形态差异性(可以由不同的字典稀疏表示)进行分离.本文详细描述了形态成分分析方法的理论思想,并介绍了形态成分分析的最新研究进展及其存在的问题,最后指出了进一步发展的方向.The separation of signal and image content into semantic parts plays a key role in applications such as analysis, enhancement, compression, restoration, and more. Although many approaches have been proposed to tackle this problem in recent years, they have many disadvantages.Morphological Component Analysis（MCA）is a novel decomposition method based on sparse representation of signals and images. The main idea of MCA is to decompose a signal or image into its building blocks considering that there is morphological diversity among a signal or an image＇ s components, which can be sparsely represented by different dictionaries. This paper introduces the theory of Morphological Component Analysis. Also, it describes the advances on morphological component analysis. Finally, several main problems have been pointed out and further research directions have been anticipated.

关 键 词：形态成分分析 稀疏表示和分解 超完备字典 

分 类 号：TP317[自动化与计算机技术—计算机软件与理论]