Image segmentation using voronoi polygons and MCMC, with application to muscle fibre images

We investigate a Bayesian method for the segmentation of muscle fibre images. The images are reasonably well approximated by a Dirichlet tessellation, and so we use a deformable template model based on Voronoi polygons to represent the segmented image. We consider various prior distributions for the parameters and suggest an appropriate likelihood. Following the Bayesian paradigm, the mathematical form for the posterior distribution is obtained (up to an integrating constant). We introduce a Metropolis-Hastings algorithm and a reversible jump Markov chain Monte Carlo algorithm (RJMCMC) for simulation from the posterior when the number of polygons is fixed or unknown. The particular moves in the RJMCMC algorithm are birth, death and position/colour changes of the point process which determines the location of the polygons. Segmentation of the true image was carried out using the estimated posterior mode and posterior mean. A simulation study is presented which is helpful for tuning the hyperparameters and to assess the accuracy. The algorithms work well on a real image of a muscle fibre cross-section image, and an additional parameter, which models the boundaries of the muscle fibres, is included in the final model.     

Asymptotic behavior of RA-estimates in autoregressive 2D processes

In this work we study the asymptotic behavior of a robust class of estimators of the coefficient of a AR-2D process. We establish the precise conditions for the consistency and asymptotic normality of the RA estimator. The AR-2D model has many applications in image modeling and statistical image processing, therefore the relevance of knowing such properties. The adequacy of the AR-2D model is analyzed with real images; we also show the impact of contamination and the capability of the RA estimator to produce useful results even in the presence of spurious data.     

Statistics,images, and pattern recognition

Data are increasingly being collected in the form of images, especially in fields using remote sensing and microscopy. Statisticians are becoming interested in developing techniques to handle the highly structured data of images. Statistical work in this area is surveyed, and two problems discussed in more detail. The first is a form of image segmentation, classifying the pixels of a satellite picture by land use. The second is the summarization of electron micrographs.     

Mixed inverse problems arising in the estimation of calibration factors in positron emission tomography

A penalized likelihood approach to the estimation of calibration factors in positron emission tomography (PET) is considered, in particular the problem of estimating the efficiency of PET detectors. Varying efficiencies among the detectors create a non-uniform performance and failure to account for the non-uniformities would lead to streaks in the image, so efficient estimation of the non-uniformities is desirable to reduce the propagation of noise to the final image. The relevant data set is provided by a blank scan, where a model may be derived that depends only on the sources affecting non-uniformities: inherent variation among the detector crystals and geometric effects. Physical considerations suggest a novel mixed inverse model with random crystal effects and smooth geometric effects. Using appropriate penalty terms, the penalized maximum likelihood estimates are derived and an efficient computational algorithm utilizing the fast Fourier transform is developed. Data-driven shrinkage and smoothing parameters are chosen to minimize an estimate of the predictive loss function. Various examples indicate that the approach proposed works well computationally and compares well with the standard method.     

Bayesian scale space analysis of temporal changes in satellite images

We consider the detection of land cover changes using pairs of Landsat ETM+ satellite images. The images consist of eight spectral bands and to simplify the multidimensional change detection task, the image pair is first transformed to a one-dimensional image. When the transformation is non-linear, the true change in the images may be masked by complex noise. For example, when changes in the Normalized Difference Vegetation Index is considered, the variance of noise may not be constant over the image and methods based on image thresholding can be ineffective. To facilitate detection of change in such situations, we propose an approach that uses Bayesian statistical modeling and simulation-based inference. In order to detect both large and small scale changes, our method uses a scale space approach that employs multi-level smoothing. We demonstrate the technique using artificial test images and two pairs of real Landsat ETM+satellite images.     

A Note on Support Vector Density Estimation for the Deconvolution Problem

The problem of support vector density estimation is studied when the sample observations are contaminated with random noise. A procedure based on support vector method and the Fourier transform is presented and is compared with kernel density estimators by the simulation study.     

Bayesian analysis of dynamic magnetic resonance breast images

Summary.  We describe an integrated methodology for analysing dynamic magnetic resonance images of the breast. The problems that motivate this methodology arise from a collaborative study with a tumour institute. The methods are developed within the Bayesian framework and comprise image restoration and classification steps. Two different approaches are proposed for the restoration. Bayesian inference is performed by means of Markov chain Monte Carlo algorithms. We make use of a Metropolis algorithm with a specially chosen proposal distribution that performs better than more commonly used proposals. The classification step is based on a few attribute images yielded by the restoration step that describe the essential features of the contrast agent variation over time. Procedures for hyperparameter estimation are provided, so making our method automatic. The results show the potential of the methodology to extract useful information from acquired dynamic magnetic resonance imaging data about tumour morphology and internal pathophysiological features.     

Quick counts from non-selected polling stations

Countless examples of misleading forecasts on behalf of both campaign and exit polls affecting, among others, British, French, and Spanish elections could be found. This has seriously damaged their image. Therefore, procedures should be used that minimize errors, especially on election night when errors are more noticeable, in order to maintain people's trust in surveys. This paper proposes a method to obtain quick and early outcome forecasts on the election night. The idea is to partly sample some (whatever) polling stations and use the consistency that polling stations show between elections to predict the final results. Model accuracy is analysed through simulation using seven different types of samples in four elections. The efficacy of the technique is also tested predicting the 2005 Eusko Legebiltzarra elections from real data. Results confirm that the procedure generates highly reliable and accurate forecasts. Furthermore, compared with the classical quick count strategy, the method is revealed as much more robust and precise.     

An approximation to cluster size distribution of two Gaussian random fields conjunction with application to FMRI data

In brain mapping, the regions of the brain that are ‘activated’ by a task or external stimulus are detected by thresholding an image of test statistics. Often the experiment is repeated on several different subjects or for several different stimuli on the same subject, and the researcher is interested in the common points in the brain where ‘activation’ occurs in all test statistic images. The conjunction is thus defined as those points in the brain that show ‘activation’ in all images. We are interested in which parts of the conjunction are noise, and which show true activation in all test statistic images. We would expect truly activated regions to be larger than usual, so our test statistic is based on the volume of clusters (connected components) of the conjunction. Our main result is an approximate P-value for this in the case of the conjunction of two Gaussian test statistic images. The results are applied to a functional magnetic resonance experiment in pain perception.     

On shape detection in noisy images with particular reference to ultrasonography

We discuss the detection of a connected shape in a noisy image. Two types of image are considered: in the first a degraded outline of the shape is visible, while in the second the data are a corrupted version of the shape itself. In the first type the shape is defined by a thin outline of pixels with records that are different from those at pixels inside and outside the shape, while in the second type the shape is defined by its edge and pixels inside and outside the shape have different records. Our motivation is the identification of cross-sectional head shapes in ultrasound images of human fetuses. We describe and discuss a new approach to detecting shapes in images of the first type that uses a specially designed filter function that iteratively identifies the outline pixels of the head. We then suggest a way based on the cascade algorithm introduced by Jubb and Jennison (1991) of improving and considerably increasing the speed of a method proposed by Storvik (1994) for detecting edges in images of the second type.     

Boundary detection through dynamic polygons

A method for the Bayesian restoration of noisy binary images portraying an object with constant grey level on a background is presented. The restoration, performed by fitting a polygon with any number of sides to the object's outline, is driven by a new probabilistic model for the generation of polygons in a compact subset of R² , which is used as a prior distribution for the polygon. Some measurability issues raised by the correct specification of the model are addressed. The simulation from the prior and the calculation of the a posteriori mean of grey levels are carried out through reversible jump Markov chain Monte Carlo computation, whose implementation and convergence properties are also discussed. One example of restoration of a synthetic image is presented and compared with existing pixel-based methods.     

Hidden Markov mesh random field models in image analysis

This paper addresses the image modeling problem under the assumption that images can be represented by third-order, hidden Markov mesh random field models. The range of applications of the techniques described hereafter comprises the restoration of binary images, the modeling and compression of image data, as well as the segmentation of gray-level or multi-spectral images, and image sequences under the short-range motion hypothesis. We outline coherent approaches to both the problems of image modeling (pixel labeling) and estimation of model parameters (learning). We derive a real-time labeling algorithm-based on a maximum, marginal a posteriori probability criterion-for a hidden third-order Markov mesh random field model. Our algorithm achieves minimum time and space complexities simultaneously, and we describe what we believe to be the most appropriate data structures to implement it. Critical aspects of the computer simulation of a real-time implementation are discussed, down to the computer code level. We develop an (unsupervised) learning technique by which the model parameters can be estimated without ground truth information. We lay bare the conditions under which our approach can be made time-adaptive in order to be able to cope with short-range motion in dynamic image sequences. We present extensive experimental results for both static and dynamic images from a wide variety of sources. They comprise standard, infra-red and aerial images, as well as a sequence of ultrasound images of a fetus and a series of frames from a motion picture sequence. These experiments demonstrate that the method is subjectively relevant to the problems of image restoration, segmentation and modeling.     

A penalized likelihood approach to image warping

A warping is a function that deforms images by mapping between image domains. The choice of function is formulated statistically as maximum penalized likelihood, where the likelihood measures the similarity between images after warping and the penalty is a measure of distortion of a warping. The paper addresses two issues simultaneously, of how to choose the warping function and how to assess the alignment. A new, Fourier–von Mises image model is identified, with phase differences between Fourier-transformed images having von Mises distributions. Also, new, null set distortion criteria are proposed, with each criterion uniquely minimized by a particular set of polynomial functions. A conjugate gradient algorithm is used to estimate the warping function, which is numerically approximated by a piecewise bilinear function. The method is motivated by, and used to solve, three applied problems: to register a remotely sensed image with a map, to align microscope images obtained by using different optics and to discriminate between species of fish from photographic images.     

Robustness of automated data choices of smoothing parameter in image regularization

Statistical image restoration techniques are oriented mainly toward modelling the image degradation process in order to recover the original image. This usually involves formulating a criterion function that will yield some optimal estimate of the desired image. Often these techniques assume that the point spread function is known when the image is restored and indeed when we estimate the smoothing parameter. However in practice this assumption may not hold. This paper investigates empirically the effect of mis-specifying the point spread function on some data-based estimates of the regularization parameter and hence on the image reconstructions. Comparisons of image reconstruction quality are based on the mean absolute difference in pixel intensities between the true and reconstructed images.     

Optimal linear projections for enhancing desired data statistics

Problems involving high-dimensional data, such as pattern recognition, image analysis, and gene clustering, often require a preliminary step of dimension reduction before or during statistical analysis. If one restricts to a linear technique for dimension reduction, the remaining issue is the choice of the projection. This choice can be dictated by desire to maximize certain statistical criteria, including variance, kurtosis, sparseness, and entropy, of the projected data. Motivations for such criteria comes from past empirical studies of statistics of natural and urban images. We present a geometric framework for finding projections that are optimal for obtaining certain desired statistical properties. Our approach is to define an objective function on spaces of orthogonal linear projections—Stiefel and Grassmann manifolds, and to use gradient techniques to optimize that function. This construction uses the geometries of these manifolds to perform the optimization. Experimental results are presented to demonstrate these ideas for natural and facial images.