ABSTRACT
Compressive sensing requires that the sensed signal is often sparse in some transform domain to enable its recovery from a small number of linear, random, multiplexed measurements. Image fusion is the process of combining two or more images to form one image. Multi-resolution representations enable fusion of image features separately at different scales. Multi-focus image fusion has become an important domain in image fusion. The simplest multi-focus image fusion method is to take pixel-by-pixel average of source images in spatial domain. Image denoising can be considered to be recovery of a signal from inaccurately and/or partially measured samples. Inexact recovery of a large matrix through matrix completion has provided new insights into the way of recovering missing data among a large set of correlated data. Wavelet-based contourlet transform, block-based random Gaussian image sampling matrix, and projection-driven compressive sensing recovery work in close cooperation in the new process framework to accomplish image reconstruction.
