A new blind image source separation algorithm based on feedback sparse component analysis

Authors:
Yu Xian-Chuan;Xu Jin-Dong;Hu Dan;Xing Hai-Hua
Affiliations:
College of Information Science and Technology, Beijing Normal University, Beijing 100875, China;College of Information Science and Technology, Beijing Normal University, Beijing 100875, China and College of Physical Engineering, Qufu Normal University, Qufu 273165, China;College of Information Science and Technology, Beijing Normal University, Beijing 100875, China;College of Information Science and Technology, Beijing Normal University, Beijing 100875, China
Venue:
Signal Processing
Year:
2013

Citing 9
Cited 1

Uniqueness of complex and multidimensional independent component analysis

Signal Processing
K-hyperline clustering learning for sparse component analysis

Signal Processing
A fast approach for overcomplete sparse decomposition based on smoothed l0 norm

IEEE Transactions on Signal Processing
An iterative Bayesian algorithm for sparse component analysis in presence of noise

IEEE Transactions on Signal Processing
Handbook of Blind Source Separation: Independent Component Analysis and Applications

Handbook of Blind Source Separation: Independent Component Analysis and Applications
Compressed sensing

IEEE Transactions on Information Theory
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries

IEEE Transactions on Image Processing
Sparsity and Morphological Diversity in Blind Source Separation

IEEE Transactions on Image Processing
Sparse component analysis and blind source separation of underdetermined mixtures

IEEE Transactions on Neural Networks

A fast mixing matrix estimation method in the wavelet domain

Signal Processing

Quantified Score

Hi-index	0.08

Visualization

Abstract

In this paper, a new blind source separation (BSS) algorithm for mixed images, called feedback sparse component analysis (FSCA), is proposed. The algorithm develops the sparse component analysis (SCA) and utilizes feedback mechanism to extract the image sources which are not sufficiently sparse to the SCA method, such as noise or complex images with low sparseness. It is experimentally shown that the proposed method does not need vast iteration and can effectively separate all un-sparse sources from the mixtures. Compared to classic fast independent component analysis (FastICA) algorithm, the presented algorithm has better accuracy.