Morphological Component Analysis: From Images to Hyperspectral Data

Prof. Jean-Luc Starck

ABSTRACT: The Morphological Component Analysis (MCA) is a a new method which allows us to separate features contained in an image when these features present different morphological aspects. MCA can be very useful for decomposing images into texture and piecewise smooth (cartoon) parts or for inpainting applications. MCA can also be extended to multichannel data (GMCA) and we show that GMCA is a very interesting alternative to standard blind source separation techniques. Finally we will see how GMCA can be used for different astronomical applications, especially for recovering the Cosmic Microwave Background from multichannel observations.