Learning Efficient Sparse and Low Rank Models.

Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with parsimony-promoting terms. The inherently sequential structure and data-dependent complexity and latency of iterative optimization constitute a major limitation in many applications requiring real-time performance or involving large-scale data. Another limitation encountered by these modeling techniques is the difficulty of their inclusion in discriminative learning scenarios. In this work, we propose to move the emphasis from the model to the pursuit algorithm, and develop a process-centric view of parsimonious modeling, in which a learned deterministic fixed-complexity pursuit process is used in lieu of iterative optimization. We show a principled way to construct learnable pursuit process architectures for structured sparse and robust low rank models, derived from the iteration of proximal descent algorithms. These architectures learn to approximate the exact parsimonious representation at a fraction of the complexity of the standard optimization methods. We also show that appropriate training regimes allow to naturally extend parsimonious models to discriminative settings. State-of-the-art results are demonstrated on several challenging problems in image and audio processing with several orders of magnitude speed-up compared to the exact optimization algorithms.

A VARIATIONAL MODEL FOR DENOISING HIGH ANGULAR RESOLUTION DIFFUSION IMAGING.

The presence of noise in High Angular Resolution Diffusion Imaging (HARDI) data of the brain can limit the accuracy with which fiber pathways of the brain can be extracted. In this work, we present a variational model to denoise HARDI data corrupted by Rician noise. Numerical experiments are performed on three types of data: 2D synthetic data, 3D diffusion-weighted Magnetic Resonance Imaging (DW-MRI) data of a hardware phantom containing synthetic fibers, and 3D real HARDI brain data. Experiments show that our model is effective for denoising HARDI-type data while preserving important aspects of the fiber pathways such as fractional anisotropy and the orientation distribution functions.

Mathematical methods for diffusion MRI processing.

In this article, we review recent mathematical models and computational methods for the processing of diffusion Magnetic Resonance Images, including state-of-the-art reconstruction of diffusion models, cerebral white matter connectivity analysis, and segmentation techniques. We focus on Diffusion Tensor Images (DTI) and Q-Ball Images (QBI).

Classification and 3D averaging with missing wedge correction in biological electron tomography.

Strategies for the determination of 3D structures of biological macromolecules using electron crystallography and single-particle electron microscopy utilize powerful tools for the averaging of information obtained from 2D projection images of structurally homogeneous specimens. In contrast, electron tomographic approaches have often been used to study the 3D structures of heterogeneous, one-of-a-kind objects such as whole cells where image-averaging strategies are not applicable. Complex entities such as cells and viruses, nevertheless, contain multiple copies of numerous macromolecules that can individually be subjected to 3D averaging. Here we present a complete framework for alignment, classification, and averaging of volumes derived by electron tomography that is computationally efficient and effectively accounts for the missing wedge that is inherent to limited-angle electron tomography. Modeling the missing data as a multiplying mask in reciprocal space we show that the effect of the missing wedge can be accounted for seamlessly in all alignment and classification operations. We solve the alignment problem using the convolution theorem in harmonic analysis, thus eliminating the need for approaches that require exhaustive angular search, and adopt an iterative approach to alignment and classification that does not require the use of external references. We demonstrate that our method can be successfully applied for 3D classification and averaging of phantom volumes as well as experimentally obtained tomograms of GroEL where the outcomes of the analysis can be quantitatively compared against the expected results.

A system for the generation of curves on 3D brain images.

In this study, a computational optimal system for the generation of curves on triangulated surfaces representing 3D brains is described. The algorithm is based on optimally computing geodesics on the triangulated surfaces following Kimmel and Sethian ([1998]: Proc Natl Acad Sci 95:15). The system can be used to compute geodesic curves for accurate distance measurements as well as to detect sulci and gyri. These curves are defined based on local surface curvatures that are computed following a novel approach presented in this study. The corresponding software is available to the research community.

Anisotropic 2-D and 3-D averaging of fMRI signals.

A novel method for denoising functional magnetic resonance imaging temporal signals is presented in this note. The method is based on progressively enhancing the temporal signal by means of adaptive anisotropic spatial averaging. This average is based on a new metric for comparing temporal signals corresponding to active fMRI regions. Examples are presented both for simulated and real two and three-dimensional data. The software implementing the proposed technique is publicly available for the research community.

Color image enhancement via chromaticity diffusion.

A novel approach for color image denoising is proposed in this paper. The algorithm is based on separating the color data into chromaticity and brightness, and then processing each one of these components with partial differential equations or diffusion flows. In the proposed algorithm, each color pixel is considered as an n-dimensional vector. The vectors' direction, a unit vector, gives the chromaticity, while the magnitude represents the pixel brightness. The chromaticity is processed with a system of coupled diffusion equations adapted from the theory of harmonic maps in liquid crystals. This theory deals with the regularization of vectorial data, while satisfying the intrinsic unit norm constraint of directional data such as chromaticity. Both isotropic and anisotropic diffusion flows are presented for this n-dimensional chromaticity diffusion flow. The brightness is processed by a scalar median filter or any of the popular and well established anisotropic diffusion flows for scalar image enhancement. We present the underlying theory, a number of examples, and briefly compare with the current literature.

Filling-in by joint interpolation of vector fields and gray levels.

A variational approach for filling-in regions of missing data in digital images is introduced. The approach is based on joint interpolation of the image gray levels and gradient/isophotes directions, smoothly extending in an automatic fashion the isophote lines into the holes of missing data. This interpolation is computed by solving the variational problem via its gradient descent flow, which leads to a set of coupled second order partial differential equations, one for the gray-levels and one for the gradient orientations. The process underlying this approach can be considered as an interpretation of the Gestaltist's principle of good continuation. No limitations are imposed on the topology of the holes, and all regions of missing data can be simultaneously processed, even if they are surrounded by completely different structures. Applications of this technique include the restoration of old photographs and removal of superimposed text like dates, subtitles, or publicity. Examples of these applications are given. We conclude the paper with a number of theoretical results on the proposed variational approach and its corresponding gradient descent flow.

Segmenting skin lesions with partial-differential-equations-based image processing algorithms.

In this paper, a partial-differential equations (PDE)-based system for detecting the boundary of skin lesions in digital clinical skin images is presented. The image is first preprocessed via contrast-enhancement and anisotropic diffusion. If the lesion is covered by hairs, a PDE-based continuous morphological filter that removes them is used as an additional preprocessing step. Following these steps, the skin lesion is segmented either by the geodesic active contours model or the geodesic edge tracing approach. These techniques are based on computing, again via PDEs, a geodesic curve in a space defined by the image content. Examples showing the performance of the algorithm are given.

Knowledge-based segmentation of SAR data with learned priors.

An approach for the segmentation of still and video synthetic aperture radar (SAR) images is described. A priori knowledge about the objects present in the image, e.g., target, shadow and background terrain, is introduced via Bayes' rule. Posterior probabilities obtained in this way are then anisotropically smoothed, and the image segmentation is obtained via MAP classifications of the smoothed data. When segmenting sequences of images, the smoothed posterior probabilities of past frames are used to learn the prior distributions in the succeeding frame. We show with examples from public data sets that this method provides an efficient and fast technique for addressing the segmentation of SAR data.

The LOCO-I lossless image compression algorithm: principles and standardization into JPEG-LS.

LOCO-I (LOw COmplexity LOssless COmpression for Images) is the algorithm at the core of the new ISO/ITU standard for lossless and near-lossless compression of continuous-tone images, JPEG-LS. It is conceived as a "low complexity projection" of the universal context modeling paradigm, matching its modeling unit to a simple coding unit. By combining simplicity with the compression potential of context models, the algorithm "enjoys the best of both worlds." It is based on a simple fixed context model, which approaches the capability of the more complex universal techniques for capturing high-order dependencies. The model is tuned for efficient performance in conjunction with an extended family of Golomb-type codes, which are adaptively chosen, and an embedded alphabet extension for coding of low-entropy image regions. LOCO-I attains compression ratios similar or superior to those obtained with state-of-the-art schemes based on arithmetic coding. Moreover, it is within a few percentage points of the best available compression ratios, at a much lower complexity level. We discuss the principles underlying the design of LOCO-I, and its standardization into JPEC-LS.

Region tracking on level-sets methods.

Since the work by Osher and Sethian on level-sets algorithms for numerical shape evolutions, this technique has been used for a large number of applications in numerous fields. In medical imaging, this numerical technique has been successfully used, for example, in segmentation and cortex unfolding algorithms. The migration from a Lagrangian implementation to a Eulerian one via implicit representations or level-sets brought some of the main advantages of the technique, i.e., topology independence and stability. This migration means also that the evolution is parametrization free. Therefore, we do not know exactly how each part of the shape is deforming and the point-wise correspondence is lost. In this note we present a technique to numerically track regions on surfaces that are being deformed using the level-sets method. The basic idea is to represent the region of interest as the intersection of two implicit surfaces and then track its deformation from the deformation of these surfaces. This technique then solves one of the main shortcomings of the very useful level-sets approach. Applications include lesion localization in medical images, region tracking in functional MRI (fMRI) visualization, and geometric surface mapping.

Shape preserving local histogram modification.

A novel approach for shape preserving contrast enhancement is presented in this paper. Contrast enhancement is achieved by means of a local histogram equalization algorithm which preserves the level-sets of the image. This basic property is violated by common local schemes, thereby introducing spurious objects and modifying the image information. The scheme is based on equalizing the histogram in all the connected components of the image, which are defined based both on the grey-values and spatial relations between pixels in the image, and following mathematical morphology, constitute the basic objects in the scene. We give examples for both grey-value and color images.

Robust anisotropic diffusion.

Relations between anisotropic diffusion and robust statistics are described in this paper. Specifically, we show that anisotropic diffusion can be seen as a robust estimation procedure that estimates a piecewise smooth image from a noisy input image. The "edge-stopping" function in the anisotropic diffusion equation is closely related to the error norm and influence function in the robust estimation framework. This connection leads to a new "edge-stopping" function based on Tukey's biweight robust estimator that preserves sharper boundaries than previous formulations and improves the automatic stopping of the diffusion. The robust statistical interpretation also provides a means for detecting the boundaries (edges) between the piecewise smooth regions in an image that has been smoothed with anisotropic diffusion. Additionally, we derive a relationship between anisotropic diffusion and regularization with line processes. Adding constraints on the spatial organization of the line processes allows us to develop new anisotropic diffusion equations that result in a qualitative improvement in the continuity of edges.

A subspace reverse-correlation technique for the study of visual neurons.

A new discrete-time reverse-correlation scheme for the study of visual neurons is proposed. The visual stimulus is generated by drawing with uniform probability, at each refresh time, an image from a finite set S of orthonormal images. We show that if the neuron can be modeled as a spatiotemporal linear filter followed by a static nonlinearity, the cross-correlation between the input image sequence and the cell's spike train output gives the projection of the receptive field onto the subspace spanned by S. The technique has been applied to the analysis of simple cells in the primary visual cortex of cats and macaque monkeys. Experimental results are presented where S spans a subspace of spatially low-pass signals. Advantages of the proposed scheme over standard white-noise techniques include improved signal to noise ratios, increased spatial resolution, and the possibility to restrict the study to particular subspaces of interest.

Constant affine velocity predicts the 1/3 power law of planar motion perception and generation.

Numerous studies have shown that the power of 1/3 is important in relating Euclidean velocity to radius of curvature (R) in the generation and perception of planar movement. Although the relation between velocity and curvature is clear and very intuitive, no valid explanation for the specific 1/3 value has yet been found. We show that if instead of computing the Euclidean velocity we compute the affine one, a velocity which is invariant to affine transformations, then we obtain that the unique function of R which will give (constant) affine invariant velocity is precisely R1/3. This means that the 1/3 power law, experimentally found in the studies of hand-drawing and planar motion perception, implies motion at constant affine velocity. Since drawing/perceiving at constant affine velocity implies that curves of equal affine length will be drawn in equal time, we performed an experiment to further support this result. Results showed agreement between the 1/3 power law and drawing at constant affine velocity. Possible reasons for the appearance of affine transformations in the generation and perception of planar movement are discussed.

Creating connected representations of cortical gray matter for functional MRI visualization.

We describe a system that is being used to segment gray matter from magnetic resonance imaging (MRI) and to create connected cortical representations for functional MRI visualization (fMRI). The method exploits knowledge of the anatomy of the cortex and incorporates structural constraints into the segmentation. First, the white matter and cerebral spinal fluid (CSF) regions in the MR volume are segmented using a novel techniques of posterior anisotropic diffusion. Then, the user selects the cortical white matter component of interest, and its structure is verified by checking for cavities and handles. After this, a connected representation of the gray matter is created by a constrained growing-out from the white matter boundary. Because the connectivity is computed, the segmentation can be used as input to several methods of visualizing the spatial pattern of cortical activity within gray matter. In our case, the connected representation of gray matter is used to create a flattened representation of the cortex. Then, fMRI measurements are overlaid on the flattened representation, yielding a representation of the volumetric data within a single image. The software is freely available to the research community.

Anisotropic diffusion of multivalued images with applications to color filtering.

A general framework for anisotropic diffusion of multivalued images is presented. We propose an evolution equation where, at each point in time, the directions and magnitudes of the maximal and minimal rate of change in the vector-image are first evaluated. These are given by eigenvectors and eigenvalues of the first fundamental form in the given image metric. Then, the image diffuses via a system of coupled differential equations in the direction of minimal change. The diffusion "strength" is controlled by a function that measures the degree of dissimilarity between the eigenvalues. We apply the proposed framework to the filtering of color images represented in CIE-L*a*b* space.