An Iteratively Reweighted Least Square Implementation for Face Recognition
نویسندگان
چکیده
We propose, as an alternative to current face recognition paradigms, an algorithm using reweighted l2 minimization, whose recognition rates are not only comparable to the random projection using l1 minimization compressive sensing method of Yang et al [5], but also robust to occlusion. Through numerical experiments, reweighted l2 mirrors the l1 solution [1] even with occlusion. Moreover, we present a theoretical analysis on the convergence of the proposed l2 approach.
منابع مشابه
A Parallel Min-Cut Algorithm using Iteratively Reweighted Least Squares
We present a parallel algorithm for the undirected s-t min-cut problem with floating-point valued weights. Our overarching algorithm uses an iteratively reweighted least squares framework. This generates a sequence of Laplacian linear systems, which we solve using parallel matrix algorithms. Our overall implementation is up to 30-times faster than a serial solver when using 128 cores.
متن کاملFast General Norm Approximation via Iteratively Reweighted Least Squares
This paper describes an efficient method for general norm approximation that appears frequently in various computer vision problems. Such a lot of problems are differently formulated, but frequently require to minimize the sum of weighted norms as the general norm approximation. Therefore we extend Iteratively Reweighted Least Squares (IRLS) that is originally for minimizing single norm. The pr...
متن کاملA comparison of typical ℓp minimization algorithms
Recently, compressed sensing has been widely applied to various areas such as signal processing, machine learning, and pattern recognition. To find the sparse representation of a vector w.r.t. a dictionary, an l1 minimization problem, which is convex, is usually solved in order to overcome the computational difficulty. However, to guarantee that the l1 minimizer is close to the sparsest solutio...
متن کاملMultiple Task Learning Using Iteratively Reweighted Least Square
Multiple task learning (MTL) is becoming popular due to its theoretical advances and empirical successes. The key idea of MTL is to explore the hidden relationships among multiple tasks to enhance learning performance. Recently, many MTL algorithms have been developed and applied to various problems such as feature selection and kernel learning. However, most existing methods highly relied on c...
متن کاملIteratively reweighted LASSO for mapping multiple quantitative trait loci
The iteratively reweighted least square (IRLS) method is mostly identical to maximum likelihood (ML) method in terms of parameter estimation and power of quantitative trait locus (QTL) detection. But the IRLS is greatly superior to ML in terms of computing speed and the robustness of parameter estimation. In conjunction with the priors of parameters, ML can analyze multiple QTL model based on B...
متن کامل