We propose a coercive approach to simultaneously register and segment multi-modal images which share similar spatial structure. Registration is done at the region level to facilitate data fusion while avoiding the need for interpolation. The algorithm performs alternating minimization of an objective function informed by statistical models for pixel values in different modalities. Hypothesis tests are developed to determine whether to refine segmentations by splitting regions. We demonstrate that our approach has significantly better performance than the state-of-the-art registration and segmentation methods on microscopy images.

This letter considers statistical estimation problems where the probability distribution of the observed random variable is invariant with respect to actions of a finite topological group. It is shown that any such distribution must satisfy a restricted finite mixture representation. When specialized to the case of distributions over the sphere that are invariant to the actions of a finite spherical symmetry group G, a group-invariant extension of the Von Mises Fisher (VMF) distribution is obtained. The G-invariant VMF is parameterized by location and scale parameters that specify the distribution's mean orientation and its concentration about the mean, respectively. Using the restricted finite mixture representation these parameters can be estimated using an Expectation Maximization (EM) maximum likelihood (ML) estimation algorithm. This is illustrated for the problem of mean crystal orientation estimation under the spherically symmetric group associated with the crystal form, e.g., cubic or octahedral or hexahedral. Simulations and experiments establish the advantages of the extended VMF EM-ML estimator for data acquired by Electron Backscatter Diffraction (EBSD) microscopy of a polycrystalline Nickel alloy sample.

This paper studies adaptive sensing for estimating the nonzero amplitudes of a sparse signal with the aim of providing analytical guarantees on the performance gain due to adaptive resource allocation. We consider a previously proposed optimal two-stage policy for allocating sensing resources. For positive powers q, we derive tight upper bounds on the mean qth-power error resulting from the optimal two-stage policy and corresponding lower bounds on the improvement over nonadaptive uniform sensing. It is shown that the adaptation gain is related to the detectability of nonzero signal components as characterized by Chernoff coefficients, thus quantifying analytically the dependence on the sparsity level of the signal, the signal-to-noise ratio (SNR), and the sensing resource budget. For fixed sparsity levels and increasing SNR or sensing budget, we obtain the rate of convergence to oracle performance and the rate at which the fraction of resources spent on the first exploratory stage decreases to zero. For a vanishing fraction of nonzero components, the gain increases without bound as a function of SNR and sensing budget. Numerical simulations demonstrate that the bounds on adaptation gain are quite tight in nonasymptotic regimes as well.

We consider distributed estimation of the inverse covariance matrix, also called the concentration matrix, in Gaussian graphical models. Traditional centralized estimation often requires iterative and expensive global inference and is therefore difficult in large distributed networks. In this paper, we propose a general framework for distributed estimation based on a maximum marginal likelihood (MML) approach. Each node independently computes a local estimate by maximizing a marginal likelihood defined with respect to data collected from its local neighborhood. Due to the non-convexity of the MML problem, we derive and consider solving a convex relaxation. The local estimates are then combined into a global estimate without the need for iterative message-passing between neighborhoods. We prove that this relaxed MML estimator is asymptotically consistent. Through numerical experiments on several synthetic and real-world data sets, we demonstrate that the two-hop version of the proposed estimator is significantly better than the one-hop version, and nearly closes the gap to the centralized maximum likelihood estimator in many situations.

We propose a multistage adaptive approach to spectrum sensing and estimation with the goal of concentrating more sensing resources on spectral components of interest. The allocation of resources to minimize the mean squared estimation error is formulated as a dynamic program. An optimal policy is given for the case of two sensing stages. For more than two stages, tractable approximate policies are developed based on open-loop feedback control (OLFC). These policies improve monotonically with the number of stages, and in particular upon the optimal two-stage policy. A spectrum sensing simulation shows substantial reductions in mean squared error compared to non-adaptive sensing and a recently proposed adaptive method. Performance gains in detecting unoccupied channels are also shown.

We propose a segmentation and anomaly detection method for electron backscatter diffraction (EBSD) images. In contrast to conventional methods that require Euler angles to be extracted from diffraction patterns, the proposed method operates on the patterns directly. We use a forward model implemented as a dictionary of diffraction patterns generated by a detailed physics-based simulation of EBSD. The combination of full diffraction patterns and a dictionary allows anomalies to be detected at the same time as grains are segmented, and also increases robustness to noise and instrument blur. The proposed method is demonstrated on a sample of the Ni-base alloy IN100.

The problem of estimation of density functionals like entropy and mutual information has received much attention in the statistics and information theory communities. A large class of estimators of functionals of the probability density suffer from the curse of dimensionality, wherein the mean squared error decays increasingly slowly as a function of the sample sizeTas the dimensiondof the samples increases. In particular, the rate is often glacially slow of orderO(T-γ/d), where γ > 0 is a rate parameter. Examples of such estimators include kernel density estimators,k-nearest neighbor (k-NN) density estimators,k-NN entropy estimators, intrinsic dimension estimators, and other examples. In this paper, we propose a weighted affine combination of an ensemble of such estimators, where optimal weights can be chosen such that the weighted estimator converges at a much faster dimension invariant rate ofO(T1). Furthermore, we show that these optimal weights can be determined by solving a convex optimization problem which can be performed offline and does not require training data. We illustrate the superior performance of our weighted estimator for two important applications: 1) estimating the Panter-Dite distortion-rate factor; and 2) estimating the Shannon entropy for testing the probability distribution of a random sample.