Freddie Åström

Image Labeling by Assignment

We introduce a novel geometric approach to the image labeling problem. Abstracting from specific labeling applications, a general objective function is defined on a manifold of stochastic matrices, whose elements assign prior data that are given in any metric space, to observed image measurements. The corresponding Riemannian gradient flow entails a set of replicator equations, one for each data point, that are spatially coupled by geometric averaging on the manifold. Starting from uniform assignments at the barycenter as natural initialization, the flow terminates at some global maximum, each of which corresponds to an image labeling that uniquely assigns the prior data. Our geometric variational approach constitutes a smooth non-convex inner approximation of the general image labeling problem, implemented with sparse interior-point numerics in terms of parallel multiplicative updates that converge efficiently.

On tensor-based PDEs and their corresponding variational formulations with application to color image denoising

The case when a partial differential equation (PDE) can be considered as an Euler-Lagrange (E-L) equation of an energy functional, consisting of a data term and a smoothness term is investigated. We show the necessary conditions for a PDE to be the E-L equation for a corresponding functional. This energy functional is applied to a color image denoising problem and it is shown that the method compares favorably to current state-of-the-art color image denoising techniques.

Color persistent anisotropic diffusion of images

Techniques from the theory of partial differential equations are often used to design filter methods that are locally adapted to the image structure. These techniques are usually used in the investigation of gray-value images. The extension to color images is non-trivial, where the choice of an appropriate color space is crucial. The RGB color space is often used although it is known that the space of human color perception is best described in terms of non-euclidean geometry, which is fundamentally different from the structure of the RGB space. Instead of the standard RGB space, we use a simple color transformation based on the theory of finite groups. It is shown that this transformation reduces the color artifacts originating from the diffusion processes on RGB images. The developed algorithm is evaluated on a set of real-world images, and it is shown that our approach exhibits fewer color artifacts compared to state-of-the-art techniques. Also, our approach preserves details in the image for a larger number of iterations.

A Tensor Variational Formulation of Gradient Energy Total Variation

We present a novel variational approach to a tensor-based total variation formulation which is called gradient energy total variation, GETV. We introduce the gradient energy tensor [6] into the GETV and show that the corresponding Euler-Lagrange (E-L) equation is a tensor-based partial differential equation of total variation type. Furthermore, we give a proof which shows that GETV is a convex functional. This approach, in contrast to the commonly used structure tensor, enables a formal derivation of the corresponding E-L equation. Experimental results suggest that GETV compares favourably to other state of the art variational denoising methods such as extended anisotropic diffusion (EAD)[1] and total variation (TV) [18] for gray-scale and colour images.

Targeted Iterative Filtering

The assessment of image denoising results depends on the respective application area, i.e. image compression, still-image acquisition, and medical images require entirely different behavior of the applied denoising method. In this paper we propose a novel, nonlinear diffusion scheme that is derived from a linear diffusion process in a value space determined by the application. We show that application-driven linear diffusion in the transformed space compares favorably with existing nonlinear diffusion techniques.

On Backward p(x)-Parabolic Equations for Image Enhancement

In this study, we investigate the backward p(x)-parabolic equation as a new methodology to enhance images. We propose a novel iterative regularization procedure for the backward p(x)-parabolic equation based on the nonlinear Landweber method for inverse problems. The proposed scheme can also be extended to the family of iterative regularization methods involving the nonlinear Landweber method. We also investigate the connection between the variable exponent p(x) in the proposed energy functional and the diffusivity function in the corresponding Euler-Lagrange equation. It is well known that the forward problems converges to a constant solution destroying the image. The purpose of the approach of the backward problems is twofold. First, solving the backward problem by a sequence of forward problems, we obtain a smooth image which is denoised. Second, by choosing the initial data properly, we try to reduce the blurriness of the image. The numerical results for denoising appear to give improvement over standard methods as shown by preliminary results.

Color image regularization via channel mixing and half quadratic minimization

In this work we introduce a variational nonconvex model for color image regularization. We express the variational problem as an instance of the half quadratic algorithm (HQA). Moreover, the generalized HQA allows us to prove convergence of the variational problem. As a demonstrator of our framework, we consider a vectorial total variation (VTV) formulation with an additional nonconvex pair-wise color-channel coupling matrix. Numerical evidence show the applicability of the proposed framework compared to VTV methods and state-of-the-art image denoising methods.

On coupled regularization for non-convex variational image enhancement

A natural continuation from conventional convex methods for image enhancement is the transition to non-convex formulations. However, strictly non-convex models do not admit traditional tools from convex optimization to be used. To resolve this drawback, non-convex problems are often cast into convex formulations by relaxing stringent assumptions on model properties. In this work we present an alternative approach. We study when an energy functional is convex given a non-convex penalty term. Key to our formulation is the introduction of a novel coupling between the discretization scheme and a non-local weight function in the data term. We interpret the non-local weights for the finite difference operators. In a denoising application we study a class of non-convex ℓp-norms. The resulting energies are globally minimized using the popular ADMM.

Image Reconstruction by Multilabel Propagation

This work presents a non-convex variational approach to joint image reconstruction and labeling. Our regularization strategy, based on the KL-divergence, takes into account the smooth geometry on the space of discrete probability distributions. The proposed objective function is efficiently minimized via DC programming which amounts to solving a sequence of convex programs, with guaranteed convergence to a critical point. Each convex program is solved by a generalized primal dual algorithm. This entails the evaluation of a proximal mapping, evaluated efficiently by a fixed point iteration. We illustrate our approach on few key scenarios in discrete tomography and image deblurring.

Numerical Integration of Riemannian Gradient Flows for Image Labeling

The image labeling problem can be described as assigning to each pixel a single element from a finite set of predefined labels. Recently, a smooth geometric approach was proposed [2] by following the Riemannian gradient flow of a given objective function on the so-called assignment manifold. In this paper, we adopt an approach from the literature on uncoupled replicator dynamics and extend it to the geometric labeling flow, that couples the dynamics through Riemannian averaging over spatial neighborhoods. As a result, the gradient flow on the assignment manifold transforms to a flow on a vector space of matrices, such that parallel numerical update schemes can be derived by established numerical integration. A quantitative comparison of various schemes reveals a superior performance of the adaptive scheme originally proposed, regarding both the number of iterations and labeling accuracy.