Blind separation of convolutive image mixtures

  • Authors:

  • Sarit Shwartz;Yoav Y. Schechner;Michael Zibulevsky

  • Affiliations:

  • Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa 32000, Israel;Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa 32000, Israel;Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa 32000, Israel

  • Venue:
  • Neurocomputing
  • Year:
  • 2008

Quantified Score

Hi-index 0.01

Visualization

Abstract

Convolutive mixtures of images are common in photography of semi-reflections. They also occur in microscopy and tomography. Their formation process involves focusing on an object layer, over which defocused layers are superimposed. We seek blind source separation (BSS) of such mixtures. However, achieving this by direct optimization of mutual information is very complex and suffers from local minima. Thus, we devise an efficient approach to solve these problems. While achieving high quality image separation, we take steps that make the problem significantly simpler than a direct formulation of convolutive image mixtures. These steps make the problem practically convex, yielding a unique global solution to which convergence can be fast. The convolutive BSS problem is converted into a set of instantaneous (pointwise) problems, using a short time Fourier transform (STFT). Standard BSS solutions for instantaneous problems suffer, however, from scale and permutation ambiguities. We overcome these ambiguities by exploiting a parametric model of the defocus point spread function. Moreover, we enhance the efficiency of the approach by exploiting the sparsity of the STFT representation as a prior. We apply our algorithm to semi-reflections, and demonstrate it in experiments.