Non-orthogonal Support Width ICA
نویسندگان
چکیده
Independent Component Analysis (ICA) is a powerful tool with applications in many areas of blind signal processing; however, its key assumption, i.e. the statistical independence of the source signals, can be somewhat restricting in some particular cases. For example, when considering several images, it is tempting to look on them as independent sources (the picture subjects are different), although they may actually be highly correlated (subjects are similar). Pictures of several landscapes (or faces) fall in this category. How to separate mixtures of such pictures? This paper proposes an ICA algorithm that can tackle this apparently paradoxical problem. Experiments with mixtures of real images demonstrate the soundness of the approach.
منابع مشابه
A Novel Non-orthogonal Joint Diagonalization Cost Function for ICA
We present a new scale-invariant cost function for non-orthogonal joint-diagonalization of a set of symmetric matrices with application to Independent Component Analysis (ICA). We derive two gradient minimization schemes to minimize this cost function. We also consider their performance in the context of an ICA algorithm based on non-orthogonal joint diagonalization.
متن کاملMinimum Support ICA Using Order Statistics. Part II: Performance Analysis
Linear instantaneous independent component analysis (ICA) is a well-known problem, for which efficient algorithms like FastICA and JADE have been developed. Nevertheless, the development of new contrasts and optimization procedures is still needed, e.g. to improve the separation performances in specific cases. For example, algorithms may exploit prior information, such as the sparseness or the ...
متن کاملSome Gradient Based Joint Diagonalization Methods for ICA
We present a set of gradient based orthogonal and nonorthogonal matrix joint diagonalization algorithms. Our approach is to use the geometry of matrix Lie groups to develop continuous-time flows for joint diagonalization and derive their discretized versions. We employ the developed methods to construct a class of Independent Component Analysis (ICA) algorithms based on non-orthogonal joint dia...
متن کاملOptimization Using Fourier Expansion over a Geodesic for Non-negative ICA
We propose a new algorithm for the non-negative ICA problem, based on the rotational nature of optimization over a set of square orthogonal (orthonormal) matrices W, i.e. where W W = WW = In. Using a truncated Fourier expansion of J(t), we obtain a Newton-like update step along the steepest-descent geodesic, which automatically approximates to a usual (Taylor expansion) Newton update step near ...
متن کاملSimple LU and QR Based Non-orthogonal Matrix Joint Diagonalization
A class of simple Jacobi-type algorithms for non-orthogonal matrix joint diagonalization based on the LU or QR factorization is introduced. By appropriate parametrization of the underlying manifolds, i.e. using triangular and orthogonal Jacobi matrices we replace a high dimensional minimization problem by a sequence of simple one dimensional minimization problems. In addition, a new scale-invar...
متن کامل