A novel technique, called augmented whole-body scanning via magnifying PET (AWSM-PET), that improves the sensitivity and lesion detectability of a PET scanner for whole-body imaging is proposed and evaluated. A Siemens Biograph Vision PET/CT scanner equipped with one or two high-resolution panel-detectors was simulated to study the effectiveness of AWSM-PET technology. The detector panels are located immediately outside the scanner's axial field-of-view (FOV). A detector panel contains 2 × 8 detector modules each consisting of 32 × 64 LSO crystals (1.0 × 1.0 × 10.0 mm3each). A22Na point source was stepped across the scanner's FOV axially to measure sensitivity profiles at different locations. An elliptical torso phantom containing 7 × 9 spherical lesions was imaged at different axial locations to mimic a multi-bed-position whole-body imaging protocol. Receiver operating characteristic (ROC) curves were analyzed to evaluate the improvement in lesion detectability by the AWSM-PET technology. Experimental validation was conducted using an existing flat-panel detector integrated with a Siemens Biograph 40 PET/CT scanner to image a torso phantom containing spherical lesions with diameters ranging from 3.3 to 11.4 mm. The contrast-recovery-coefficient (CRC) of the lesions was evaluated for the scanner with or without the AWSM-PET technology. Monte Carlo simulation shows 36%-42% improvement in system sensitivity by a dual-panel AWSM-PET device. The area under the ROC curve is 0.962 by a native scanner for the detection of 4 mm diameter lesions with 5:1 tumor-to-background activity concentration. It was improved to 0.977 and 0.991 with a single- and dual-panel AWSM-PET system, respectively. Experimental studies showed that the average CRC of 3.3 mm and 4.3 mm diameter tumors were improved from 2.8% and 4.2% to 7.9% and 11.0%, respectively, by a single-panel AWSM-PET device. With a high-sensitivity dual-panel device, the corresponding CRC can be further improved to 11.0% and 15.9%, respectively. The principle of the AWSM-PET technology has been developed and validated. Enhanced system sensitivity, CRC and tumor detectability were demonstrated by Monte Carlo simulations and imaging experiments. This technology may offer a cost-effective path to realize high-resolution whole-body PET imaging clinically.

Engineering educators have struggled with engaging students throughout their studies. Traditional coursework provides little opportunity for holistic integration, personal connection, and professional relevance. We have integrated high-impact practices within our required curriculum. One element is a new, required, one-credit seminar for students beginning their engineering coursework. The seminar is very student-centered, dominated by discussions connecting technical concepts with real-world context. The lecturer is a professional engineer; he hosts visiting engineers to discussions. The course modules foster understanding in ethics, professionalism, community needs, and connection to industry and government. In a second element, we have also integrated new integrative modules into existing capstone seminars within each major. This novel pairing provides students opportunities for reflection and integration within required coursework. Our overall goal is to cultivate a learning community of the whole, within which students experience their coursework in constant contact with the broader world and with persistent progress toward their own holistic education.

We propose a new algorithm, called line integral alternating minimization (LIAM), for dual-energy X-ray CT image reconstruction. Instead of obtaining component images by minimizing the discrepancy between the data and the mean estimates, LIAM allows for a tunable discrepancy between the basis material projections and the basis sinograms. A parameter is introduced that controls the size of this discrepancy, and with this parameter the new algorithm can continuously go from a two-step approach to the joint estimation approach. LIAM alternates between iteratively updating the line integrals of the component images and reconstruction of the component images using an image iterative deblurring algorithm. An edge-preserving penalty function can be incorporated in the iterative deblurring step to decrease the roughness in component images. Images from both simulated and experimentally acquired sinograms from a clinical scanner were reconstructed by LIAM while varying the regularization parameters to identify good choices. The results from the dual-energy alternating minimization algorithm applied to the same data were used for comparison. Using a small fraction of the computation time of dual-energy alternating minimization, LIAM achieves better accuracy of the component images in the presence of Poisson noise for simulated data reconstruction and achieves the same level of accuracy for real data reconstruction.

We propose a globally convergent alternating minimization (AM) algorithm for image reconstruction in transmission tomography, which extends automatic relevance determination (ARD) to Poisson noise models with Beer's law. The algorithm promotes solutions that are sparse in the pixel/voxel--difference domain by introducing additional latent variables, one for each pixel/voxel, and then learning these variables from the data using a hierarchical Bayesian model. Importantly, the proposed AM algorithm is free of any tuning parameters with image quality comparable to standard penalized likelihood methods. Our algorithm exploits optimization transfer principles which reduce the problem into parallel one-dimensional optimization tasks (one for each pixel/voxel), making the algorithm feasible for large-scale problems. This approach considerably reduces the computational bottleneck of ARD associated with the posterior variances. Positivity constraints inherent in transmission tomography problems are also enforced. We demonstrate the performance of the proposed algorithm for x-ray computed tomography using synthetic and real-world datasets. The algorithm is shown to have much better performance than prior ARD algorithms based on approximate Gaussian noise models, even for high photon flux. Sample code is available from http://www.yan-kaganovsky.com/\#!code/c24bp.

The electrical signal originating from the heart, the electrocardiogram (ECG), has been examined for its potential use as a biometric. Recent ECG studies have shown that an intersession authentication performance$\sim 2$% EER. Moreover, in the identification mode, with a testing database containing 200 individuals, the rank-1 accuracy improves from$\sim 80$% for each individual biometric system, to$\sim 92$% for the multibiometric system. Although there are implementation issues that would need to be resolved before this combined method could be applied in the field, this report establishes the basis and utility of the method in principle, and it identifies effective signal analysis approaches.

The electrocardiogram (ECG) is an emerging biometric modality that has seen about 13 years of development in peer-reviewed literature, and as such deserves a systematic review and discussion of the associated methods and findings. In this paper, we review most of the techniques that have been applied to the use of the electrocardiogram for biometric recognition. In particular, we categorize the methodologies based on the features and the classification schemes. Finally, a comparative analysis of the authentication performance of a few of the ECG biometric systems is presented, using our inhouse database. The comparative study includes the cases where training and testing data come from the same and different sessions (days). The authentication results show that most of the algorithms that have been proposed for ECG-based biometrics perform well when the training and testing data come from the same session. However, when training and testing data come from different sessions, a performance degradation occurs. Multiple training sessions were incorporated to diminish the loss in performance. That notwithstanding, only a few of the proposed ECG recognition algorithms appear to be able to support performance improvement due to multiple training sessions. Only three of these algorithms produced equal error rates (EERs) in the single digits, including an EER of 5.5% using a method proposed by us.

We consider the trade-off between identification and secret-key binding capacities in biometric systems. We propose the use of linear codes to achieve optimal trade-off for general source and noise models. We relate the problem to classical point to point communication problems, and two system designs based on linear codes are discussed. One design is proven to achieve optimal trade-off by using good linear codes and good decoders. The other design can be proven to achieve slightly suboptimal performance with lower decoder complexity, which is proper for many practical situations. Based on these results, we are also able to extend previous achievable rate region results to general source and noise models that have dependency within and across source and noise elements.

In real life, one often encounters situations where one needs to infer a structural relationship among data points based on an incomplete dataset. Stemmatology and phylogenetics are two classes of such problems where partial text scripts or genome sequences are available and the goal is to reconstruct the copying history of scripts or evolutionary relations among species. In this paper, we study the potential applications of minimum description length (MDL) concepts to the structural inference problem, particularly focusing on stemmatology where in addition to missing data points, the available data points have missing values. We offer new insights on how to handle these issues, especially missing values. We develop a general algorithm based on MDL insights that is simple to implement and can be used along with other existing algorithms, and propose a generic MDL encoder with minimal assumptions made about the data. In simulations, our method performs reasonably well on a simple dataset and outperforms major existing methods in a larger and much more realistic dataset. We discuss directions and ongoing efforts to further improve performance.

A novel approach for remotely sensing mechanical cardiovascular activity for use as a biometric marker is proposed. Laser Doppler Vibrometry (LDV) is employed to sense vibrations on the surface of the skin above the carotid artery related to arterial wall movements associated with the central blood pressure pulse. Carotid LDV signals are recorded using noncontact methods and the resulting unobtrusiveness is a major benefit of this technique. Several recognition methods are proposed that use the temporal and/or spectral information in the signal to assess biometric performance both on an intrasession basis, and on an intersession basis where LDV measurements were acquired from the same subjects after delays ranging from one week to six months. A waveform decomposition method that utilizes principal component analysis is used to model the signal in the time domain. Authentication testing for this approach produces an equal-error rate of 0.5% for intrasession testing. However, performance degrades substantially for intersession testing, requiring a more robust approach to modeling. Improved performance is obtained using techniques based on time-frequency decomposition, incorporating a method for extracting informative components. Biometric fusion methods including data fusion and information fusion are applied to train models using data from multiple sessions. As currently implemented, this approach yields an intersession equal-error rate of 6.3%.

Many wireless sensor networks require sufficient sensing coverage over long periods of time. To conserve energy, a coverage maintenance protocol achieves desired coverage by activating only a subset of nodes, while allowing the others to sleep. Existing coverage maintenance protocols are often designed based on simplistic sensing models that do not capture the stochastic nature of distributed sensing. We propose a new sensing coverage model based on the distributed detection theory, which captures two important characteristics of sensor networks, i.e., probabilistic detection by individual sensors and data fusion among sensors. We then present three coverage maintenance protocols that can meet the specified event detection probability and false alarm rate. The centralized protocol only activates a small number of sensors, but introduces extremely long coverage configuration delay. The Se-Grid protocol reduces the configuration time by dividing the network into separate fusion groups, but increases the number of active sensors due to the lack of collaboration among sensors in different groups. In contrast, by coordinating overlapping fusion groups, the Co-Grid protocol can effectively reduce the number of active sensors and the coverage configuration time. The advantages of Co-Grid have been validated through simulations and benchmark results on Mica2 motes.

We propose an information-theoretic clustering framework for density-based clustering and similarity or distance-based clustering with objective functions of clustering performance derived from stochastic complexity and minimum description length (MDL) arguments. Under this framework, the number of clusters and parameters can be determined in a principled way without prior knowledge from users. We show that similarity-based clustering can be viewed as combinatorial optimization on graphs. We propose two clustering algorithms, one of which relies on a minimum arborescence tree algorithm which returns optimal clustering under the proposed MDL objective function for similarity-based clustering. We demonstrate clustering performance on synthetic data.

Biological and machine pattern recognition systems face a common challenge: Given sensory data about an unknown pattern, classify the pattern by searching for the best match within a library of representations stored in memory. In many cases, the number of patterns to be discriminated and the richness of the raw data force recognition systems to internally represent memory and sensory information in a compressed format. However, these representations must preserve enough information to accommodate the variability and complexity of the environment, otherwise recognition will be unreliable. Thus, there is an intrinsic tradeoff between the amount of resources devoted to data representation and the complexity of the environment in which a recognition system may reliably operate. In this paper, we describe a mathematical model for pattern recognition systems subject to resource constraints, and show how the aforementioned resource-complexity tradeoff can be characterized in terms of three rates related to the number of bits available for representing memory and sensory data, and the number of patterns populating a given statistical environment. We prove single-letter information-theoretic bounds governing the achievable rates, and investigate in detail two illustrative cases where the pattern data is either binary or Gaussian.

Pattern recognition systems based on compressed patterns and compressed sensor measurements can be designed using low-density matrices. We examine truncation encoding where a subset of the patterns and measurements are stored perfrectly while the rest is discarded. We also examine the use of LDPC parity check matrices for compressing measurements and patterns. We show how more general ensembles of good linear codes can be used as the basis for pattern recognition system design, yielding system design strategies for more general noise models.

A family of alternating minimization algorithms for finding maximum-likelihood estimates of attenuation functions in transmission X-ray tomography is described. The model from which the algorithms are derived includes polyenergetic photon spectra, background events, and nonideal point spread functions. The maximum-likelihood image reconstruction problem is reformulated as a double minimization of the I-divergence. A novel application of the convex decomposition lemma results in an alternating minimization algorithm that monotonically decreases the objective function. Each step of the minimization is in closed form. The family of algorithms includes variations that use ordered subset techniques for increasing the speed of convergence. Simulations demonstrate the ability to correct the cupping artifact due to beam hardening and the ability to reduce streaking artifacts that arise from beam hardening and background events.

We study the influence of the variation in the shape of the pits for the two-dimensional optical storage (TwoDOS) paradigm vis-à-vis the readback signal and decoding performance. The algorithm used for decoding is a message-passing based joint equalization and decoding algorithm proposed by Singla and O'Sullivan (Intl. Symp. Info. Theory, Sept. 2005). The performance dependence of the algorithm on pit shape is studied by comparing the noise-tolerance thresholds for the algorithm. The TwoDOS model under consideration also includes two forms of media noise: pit-position noise, arising due to the deviation in the location of the pits from their intended positions and pit-size noise, arising due to variations in the radii of the pits. It is shown that as the shape of the pit changes from the ideal cylindrical shape towards a conical shape there is a sharp decrease in the range of the signal intensity. This decrease in the range leads to increased signal folding which is detrimental for the decoding algorithm. However, we show that when the ratio of the area of the pit to the area of the hexagonal bit cell is large (~1) then the extent of signal folding for a conical profile is actually less than that of a cylindrical profile. Then, in this case, the performance of the decoder for a conical profile is better than for a cylindrical profile.

In this paper we examine the achievable rate region for the problem of successive refinement of information for pattern recognition systems. The pattern recognition system has two stages, going from coarse to fine recognition as more resources become available for storing internal representations of the patterns. We present an inner and an outer bound on the true achievable rate region. Using these results we derive conditions under which a pattern recognition system is successively refinable. These conditions are similar to the Markov condition for successive refinement in the rate-distortion problem.

We address the problem of image formation in transmission tomography when metal objects of known composition and shape, but unknown pose, are present in the scan subject. Using an alternating minimization (AM) algorithm, derived from a model in which the detected data are viewed as Poisson-distributed photon counts, we seek to eliminate the streaking artifacts commonly seen in filtered back projection images containing high-contrast objects. We show that this algorithm, which minimizes the I-divergence (or equivalently, maximizes the log-likelihood) between the measured data and model-based estimates of the means of the data, converges much faster when knowledge of the high-density materials (such as brachytherapy applicators or prosthetic implants) is exploited. The algorithm incorporates a steepest descent-based method to find the position and orientation (collectively called the pose) of the known objects. This pose is then used to constrain the image pixels to their known attenuation values, or, for example, to form a mask on the "missing" projection data in the shadow of the objects. Results from two-dimensional simulations are shown in this paper. The extension of the model and methods used to three dimensions is outlined.

Pattern recognition systems may be designed to recognize an exponentially large number of objects from potentially noisy measurements. We propose a design based on storing compressed representations of binary patterns corresponding to objects of interest. Sensor measurements are similarly compressed and recognition proceeds by comparing the compressed sensor measurements to the compressed representations of the objects. Parity check matrices corresponding to low density parity check codes are used for the compression. This design yields an ensemble of systems such that the probability of error goes to zero as the length of the patterns grows

An algorithm that performs joint equalization and decoding for channels with nonlinear two-dimensional intersymbol interference is presented. The algorithm performs sum-product message-passing on a factor graph that represents the underlying system. The two-dimensional optical storage (Two-DOS) technology is an example of a system with nonlinear two-dimensional intersymbol interference. Simulations for the nonlinear channel model of TwoDOS show significant improvement in performance over uncoded performance. Noise tolerance thresholds for the TwoDOS channel computed using density evolution are also presented

Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian

Wireless sensor networks often face the critical challenge of sustaining long-term operation on limited battery energy. Coverage maintenance protocols can effectively prolong network lifetime by maintaining sufficient sensing coverage over a region using a small number of active nodes while scheduling the others to sleep. We present a novel distributed coverage maintenance protocol called the Coordinating Grid (Co-Grid). In contrast to existing coverage maintenance protocols which are based on simpler detection models, Co-Grid adopts a distributed detection model based on data fusion that is more consistent with many distributed sensing applications. Co-Grid organizes the network into coordinating fusion groups located on overlapping virtual grids. Through coordination among neighboring fusion groups, Co-Grid can achieve comparable number of active nodes as a centralized algorithm, while reducing the network (re-)configuration time by orders of magnitude. Co-Grid is especially suitable for large and energy-constrained sensor networks that require quick (re-)configuration in response to node failures and environmental changes. We validate our claims by both theoretical analysis and simulations.

Joint iterative equalization and decoding schemes are proposed for two-dimensional inter-symbol interference channels. Equalization is performed using the minimum mean squared error criterion. Three linear equalizers are proposed. The exact equalizer, a spatially and temporally varying equalizer, has performance similar to schemes based on message-passing and has lower complexity. To save further on computational cost, time-invariant implementations of the exact equalizer are also proposed. Extrinsic information transfer charts are used to analyze the equalizers. A density evolution algorithm using a Gaussian approximation is proposed and used to study the trade-off between computational cost and performance for different decoding schedules.

We propose a model for rate-constrained pattern recognition problems, and present single-letter information bounds governing the conditions under which asymptotically error-free recognition is possible. The bounds depend on the statistics of the training and testing data, the number of pattern classes, and the rates of the codes used by the recognition system to internalize the data.

Many applications of object recognition in the presence of pose uncertainty rely on statistical models-conditioned on pose-for observations. The image statistics of three-dimensional (3-D) objects are often assumed to belong to a family of distributions with unknown model parameters that vary with one or more continuous-valued pose parameters. Many methods for statistical model assessment, for example the tests of Kolmogorov-Smirnov and K. Pearson, require that all model parameters be fully specified or that sample sizes be large. Assessing pose-dependent models from a finite number of observations over a variety of poses can violate these requirements. However, a large number of small samples, corresponding to unique combinations of object, pose, and pixel location, are often available. We develop methods for model testing which assume a large number of small samples and apply them to the comparison of three models for synthetic aperture radar images of 3-D objects with varying pose. Each model is directly related to the Gaussian distribution and is assessed both in terms of goodness-of-fit and underlying model assumptions, such as independence, known mean, and homoscedasticity. Test results are presented in terms of the functional relationship between a given significance level and the percentage of samples that wold fail a test at that level.

An information-theoretic analysis of information hiding is presented, forming the theoretical basis for design of information-hiding systems. Information hiding is an emerging research area which encompasses applications such as copyright protection for digital media, watermarking, fingerprinting, steganography, and data embedding. In these applications, information is hidden within a host data set and is to be reliably communicated to a receiver. The host data set is intentionally corrupted, but in a covert way, designed to be imperceptible to a casual analysis. Next, an attacker may seek to destroy this hidden information, and for this purpose, introduce additional distortion to the data set. Side information (in the form of cryptographic keys and/or information about the host signal) may be available to the information hider and to the decoder. We formalize these notions and evaluate the hiding capacity, which upper-bounds the rates of reliable transmission and quantifies the fundamental tradeoff between three quantities: the achievable information-hiding rates and the allowed distortion levels for the information hider and the attacker. The hiding capacity is the value of a game between the information hider and the attacker. The optimal attack strategy is the solution of a particular rate-distortion problem, and the optimal hiding strategy is the solution to a channel-coding problem. The hiding capacity is derived by extending the Gel'fand-Pinsker (1980) theory of communication with side information at the encoder. The extensions include the presence of distortion constraints, side information at the decoder, and unknown communication channel. Explicit formulas for capacity are given in several cases, including Bernoulli and Gaussian problems, as well as the important special case of small distortions. In some cases, including the last two above, the hiding capacity is the same whether or not the decoder knows the host data set. It is shown that many existing information-hiding systems in the literature operate far below capacity.

The implementation of computational systems to perform challenging operations often involves balancing the performance specification, system throughput, and available system resources. For problems of automatic target recognition (ATR), these three quantities of interest are the probability of classification error, the rate at which regions of interest are processed, and the capabilities of the underlying hardware (which is a function of the available computational resources and available power). An understanding of the inter-relationships between these factors can be an aid in making informed choices while exploring competing design possibilities. Combining characterizations of ATR performance, which yield probability of classification error as a function of target model complexity, with analytical models of computational performance, which yield throughput as a function of target model complexity and available resources, we can form a set of parametric curves which relate the quality of the results to the resources consumed.

We generalize the axiomatic quantification of one-dimensional (1-D) image resolution to the multidimensional case. The imaging system of interest is characterized by a nonnegative spatially invariant point spread function. The axioms extended from the 1-D counterparts include nonnegativity, continuity, translation invariance, rotation invariance, luminance invariance, homogeneous scaling, and serial combination properties. It is proved that the only resolution measure consistent with the axioms is proportional to the square root of the trace of the covariance matrix of the point spread function.

In physical signature authentication schemes, a candidate signature presented for authentication is compared to a previous signature measurement. The uniqueness of a signature is a result of a random physical process underlying the signature formation. We model signatures as realizations of random processes with known statistics. Rate functions for the false alarm and miss probabilities are determined. The case where the candidate signature and previous signature measurement are zero-mean, stationary, and Gaussian is covered in detail, yielding quantitative measures of performance for system design. The binary case is also discussed.

Often recognition systems must be designed with a relatively small amount of training data. Plug-in test statistics suffer from large estimation errors, often causing the performance to degrade as the measurement vector dimension increases. Choosing a better test statistic or applying a method of dimensionality reduction are two possible solutions to this problem. In this paper, we consider a recognition problem where the data for each population are assumed to have the same parametric distribution but differ in their unknown parameters. The collected vectors of data as well as their components are assumed to be independent. The system is designed to implement a plug-in log-likelihood ratio test with maximum-likelihood (ML) estimates of the unknown parameters instead of the true parameters. Because a small amount of data is available to estimate the parameters, the performance of such a system is strongly degraded relative to the performance with known parameters. To improve the performance of the system we define a thresholding function that, when incorporated into the plug-in log-likelihood ratio, significantly decreases the probability of error for binary and multiple hypothesis testing problems for the exponential class of populations. We analyze the modified test statistic and present the results of Monte Carlo simulation. Special attention is paid to the complex Gaussian model with zero mean and unknown variances.

The reconstruction of tomographic images is often treated as a linear deblurring problem. When a high-density, man-made metal object is present somewhere in the image field, it is a deblurring problem in which the unknown function has a component that is known except for some location and orientation parameters. We first address general linear deblurring problems in which a known function having unknown parameters is present. We then show how the resulting iterative solution can be applied to tomographic imaging in the presence of man-made foreign objects, and we apply the result, in particular, to X-ray computed tomography imaging used in support of brachytherapy treatment of advanced cervical cancer.

An information-theoretic analysis of watermarking is presented in this paper. We formulate watermarking as a communication problem with side information at the encoder and decoder and determine the hiding capacity, which upper-bounds the rates of reliable transmission and quantifies the fundamental tradeoff between three quantities: the achievable watermarking rates and the allowed distortion levels for the information hider and the attacker. The hiding capacity is the value of a game between the information hider and the attacker. The optimal attack strategy is the solution of a particular rate-distortion problem, and the optimal hiding strategy is the solution to a channel coding problem. For several important problems, the hiding capacity is the same whether or not the decoder knows the host data set. It is also shown that existing watermarking systems in the literature operate far below capacity.

The emergent role of information theory in image formation is surveyed. Unlike the subject of information-theoretic communication theory, information-theoretic imaging is far from a mature subject. The possible role of information theory in problems of image formation is to provide a rigorous framework for defining the imaging problem, for defining measures of optimality used to form estimates of images, for addressing issues associated with the development of algorithms based on these optimality criteria, and for quantifying the quality of the approximations. The definition of the imaging problem consists of an appropriate model for the data and an appropriate model for the reproduction space, which is the space within which image estimates take values. Each problem statement has an associated optimality criterion that measures the overall quality of an estimate. The optimality criteria include maximizing the likelihood function and minimizing mean squared error for stochastic problems, and minimizing squared error and discrimination for deterministic problems. The development of algorithms is closely tied to the definition of the imaging problem and the associated optimality criterion. Algorithms with a strong information-theoretic motivation are obtained by the method of expectation maximization. Related alternating minimization algorithms are discussed. In quantifying the quality of approximations, global and local measures are discussed. Global measures include the (mean) squared error and discrimination between an estimate and the truth, and probability of error for recognition or hypothesis testing problems. Local measures include Fisher information.

Proposes a framework for simultaneous detection, tracking, and recognition of objects via data fused from multiple sensors. Complex dynamic scenes are represented via the concatenation of simple rigid templates. The variability of the infinity of pose is accommodated via the actions of matrix Lie groups extending the templates to individual instances. The variability of target number and target identity is accommodated via the representation of scenes as unions of templates of varying types, with the associated group transformations of varying dimension. We focus on recognition in the air-to-ground and ground-to-air scenarios. The remote sensing data is organized around both the coarse scale associated with detection as provided by tracking and range radars, along with the fine scale associated with pose and identity supported by high-resolution optical, forward looking infrared and delay-Doppler radar imagers. A Bayesian approach is adopted in which prior distributions on target scenarios are constructed via dynamical models of the targets of interest. These are combined with physics-based sensor models which define conditional likelihoods for the coarse/fine scale sensor data given the underlying scene. Inference via the Bayes posterior is organized around a random sampling algorithm based on jump-diffusion processes. New objects are detected and object identities are recognized through discrete jump moves through parameter space, the algorithm exploring scenes of varying complexity as it proceeds. Between jumps, the scale and rotation group transformations are generated via continuous diffusions in order to smoothly deform templates into individual instances of objects.

Iterative deblurring methods using the expectation maximization (EM) formulation and the algebraic reconstruction technique (ART), respectively, are adapted for metal artifact reduction in medical computed tomography (CT). In experiments with synthetic noise-free and additive noisy projection data of dental phantoms, it is found that both simultaneous iterative algorithms produce superior image quality as compared to filtered backprojection after linearly fitting projection gaps. Furthermore, the EM-type algorithm converges faster than the ART-type algorithm in terms of either the I-divergence or Euclidean distance between ideal and reprojected data in the authors' simulation. Also, for a given iteration number, the EM-type deblurring method produces better image clarity but stronger noise than the ART-type reconstruction. The computational complexity of EM- and ART-based iterative deblurring is essentially the same, dominated by reprojection and backprojection. Relevant practical and theoretical issues are discussed.

A class of penalty functions for use in estimation and image regularization is proposed. These penalty functions are defined for vectors whose indexes are locations in a finite lattice as the discrepancy between the vector and a shifted version of itself. After motivating this class of penalty functions, their relationship to Markov random field priors is explored. One of the penalty functions proposed, a divergence roughness penalty, is shown to be a discretization of a penalty proposed by Good and Gaskins (1971) for use in density estimation. One potential use in estimation problems is explored. An iterative algorithm that takes advantage of induced neighborhood structures is proposed and convergence of the algorithm is proven under specified conditions. Examples in emission tomographic imaging and radar imaging are given.

This paper discusses a new roughness penalty for use in estimation problems including image estimation problems. It is one of a new class of penalty functions for use in estimation and image regularization that has recently been proposed. These functions penalize the discrepancy between an image and a shifted version of itself; here the discrepancy measure is the I-divergence. This penalty is closely related to a penalty used for density estimation that was introduced by Good and Gaskins (1971). Roughness penalty methods form an attractive alternative to Markov random field priors, achieving many of the same properties including the introduction of neighborhood structures. An example of the use of this new penalty for radar imaging using real radar data has been examined.>

The entropies and combinatorics of trees that branch according to fixed but finite numbers of rules are studied. Context-free grammars are used to categorize the ways in which nodes branch to yield daughter nodes, thus providing an organized setting to examine the entropies for random branching processes whose realizations are trees and whose probabilities are determined by probabilities associated with the substitution rules of the grammar. Normalized entropy rates H are derived for the critical branching rate and supercritical branching rate processes. An equipartition theorem is proved for the supercritical processes. A strong departure from classical theorems for Markov sources occurs for supercritical branching processes as the typical sets have supergeometric growth rates. The combinatorics of the set of all trees that can be generated from the context-free substitution rules is also studied.>

A method of sieves using splines is proposed for regularizing maximum-likelihood estimates of power spectra. This method has several important properties, including the flexibility to be used at multiple resolution levels. The resolution level is defined in terms of the support of the polynomial B-splines used. An expression for the optimal rate of growth of the sieve is derived using a discrepancy measure derived from the Kullback-Leibler divergence of parameterized density functions. While the sieves may be defined on nonuniform grids, in the case of uniform grids the optimal sieve size corresponds to an optimal resolution. Iterative algorithms for obtaining the maximum-likelihood sieve estimates are derived. Applications to spectrum estimation and radar imaging are proposed.>

A general method is proposed for incorporating rule-based constraints corresponding to regular languages into stochastic inference problems, thereby allowing for a unified representation of stochastic and syntactic pattern constraints. The authors' approach establishes the formal connection of rules to Chomsky grammars and generalizes the original work of Shannon on the encoding of rule-based channel sequences to Markov chains of maximum entropy. This maximum entropy probabilistic view leads to Gibbs representations with potentials which have their number of minima growing at precisely the exponential rate that the language of deterministically constrained sequences grow. These representations are coupled to stochastic diffusion algorithms, which sample the language-constrained sequences by visiting the energy minima according to the underlying Gibbs probability law. This coupling yields the result that fully parallel stochastic cellular automata can be derived to generate samples from the rule-based constraint sets. The production rules and neighborhood state structure of the language of sequences directly determine the necessary connection structures of the required parallel computing surface. Representations of this type have been mapped to the DAP-510 massively parallel processor consisting of 1024 mesh-connected bit-serial processing elements for performing automated segmentation of electron-micrograph images.

A novel approach is developed for forming high-resolution images of radar targets from delay Doppler spotlight-mode radar data. This approach is based on a model for the target's reflectivity in terms of wide-sense stationary, uncorrelated scatterers having complex-valued Gaussian statistics. The imaging problem is to estimate the target's scattering function in terms of radar-echo data acquired with a series of target illuminations. A method is developed for solving this multidimensional spectrum estimation problem through the use of maximum-likelihood estimation implemented using the expectation-maximization algorithm.>

An approach to high-resolution imaging that starts with a model of the radar echo signal derived from the physics governing radar reflections is presented. The model has been used in the past to describe radar targets that are rough compared to the wavelength of the transmitted radiation. Without specifying precisely what the transmitted signal is, a general estimation-based procedure is derived for obtaining images. After discretizing the model, the radar imaging problem reduces to the task of estimating discretized second-order statistics of the reflectance process of the target. Maximum-likelihood estimates of these statics are obtained as the limit point of an expectation-maximization algorithm.>