Improved 2D vector field estimation using probabilistic weights.

We consider the application of tomography to the reconstruction of two-dimensional vector fields. The most practical sensor configuration in such problems is the regular positioning along the boundary of the reconstruction domain. However, such a configuration does not result in uniform distribution in the Radon parameter space, which is a necessary requirement to achieve accurate reconstruction results. On the other hand, sampling the projection space uniformly imposes serious constraints on space or time. In this paper, we propose to place the sensors regularly along the boundary of the reconstruction domain and employ probabilistic weights with the purpose of compensating for the lack of uniformity in the distribution of projection space parameters. Simulation results demonstrate that, when the proposed probabilistic weights are employed, an average 27% decrease in the reconstruction error may be achieved, over the case that projection measurements are not weighed (e.g., in one case the error reduces from 3.7% to 2.6%). When compared with the case where actual uniform sampling of the projection space is employed, the proposed method achieves a 90 times reduction in the number of the required sensors or 180 times reduction in the total scanning time, with only 7% increase in the error with which the vector field is estimated.

Virtual sensors for 2D vector field tomography.

We consider the application of tomography to the reconstruction of 2-D vector fields. The most convenient sensor configuration in such problems is the regular positioning along the domain boundary. However, the most accurate reconstructions are obtained by sampling uniformly the Radon parameter domain rather than the border of the reconstruction domain. This dictates a prohibitively large number of sensors and impractical sensor positioning. In this paper, we propose uniform placement of the sensors along the boundary of the reconstruction domain and interpolation of the measurements for the positions that correspond to uniform sampling in the Radon domain. We demonstrate that when the cubic spline interpolation method is used, a 60 times reduction in the number of sensors may be achieved with only about 10% increase in the error with which the vector field is estimated. The reconstruction error by using the same sensors and ignoring the necessity of uniform sampling in the Radon domain is in fact higher by about 30%. The effects of noise are also examined.

Design of a wire-mesh collimator for gamma cameras.

This paper presents a model of a wire-mesh collimator for a gamma camera that produces images of comparable quality as those produced with the conventional multihole collimator, but has about half the weight of the multihole collimator. The gamma camera and the collimator are simulated using the MCNPX code. Two final configurations of the wire-mesh collimator are proposed, and their performance is compared with other wire-mesh collimators and with the multihole collimator, using a point source, a planar square source, and two point sources, all in water. In all cases, photons with energy 140 keV are simulated. In addition, we use the simulation of a realistic phantom of a hot tumor in a warm background to assess the performance of our collimator in conjunction with an extended source.

The "invaders" algorithm: range of values modulation for accelerated correlation.

In this paper, we present an algorithm that allows the simultaneous calculation of several cross correlations. The algorithm works by shifting the range of values of different images/signals to occupy different orders of magnitude and then combining them to form a single composite image/signal. Because additional signals are placed in the space usually occupied by a single signal, we call this the "invaders algorithm," to imply that extra signals invade the space that normally belongs to a single signal. After correlation is performed, the individual results are recovered by performing the inverse operation. The limitations of the algorithm are imposed by the finite length of the mantissa of the hardware used, the precision of the algorithm that performs the cross correlation (e.g., the precision of the fast Fourier transform (FFT)) and by the actual values of the images/signals that are to be combined. The algorithm does not require any special hardware or special FFT algorithm. For typical 256 x 256 images, an acceleration by a factor of at least two in the calculation of their cross correlations is guaranteed using an ordinary PC or a laptop. As for smaller sized templates, tenfold accelerations may be achieved.

Affine parameter estimation from the trace transform.

In this paper, we assume that we are given the images of two segmented objects, one of which may be an affinely distorted version of the other, and wish to recover the values of the parameters of the affine transformation between the two images. The images may also differ by the overall level of illumination. The multiplicative constant of such difference may also be recovered. We present a generic theoretical framework to solve this problem. In terms of this framework, other proposed methods may be interpreted. We show how, in this framework, one can recover the affine parameters in a way that is robust to various effects, such as occlusion and illumination variation. The proposed method is generic enough to be applicable also to matching two images that do not depict the same scene or object.

Image registration using the Walsh transform.

This paper presents a new algorithm which can be used to register images of the same or different modalities, e.g., images with multiple channels, such as X-rays, temperature or elevation, or simply images of different spectral bands. In particular, a correlation-based scheme is used, but instead of gray values, it correlates numbers formulated by different combinations of the extracted local Walsh coefficients of the images. Each image patch is expanded in terms of Walsh basis functions. Each Walsh basis function can be thought of as measuring a different aspect of local structure, e.g., horizontal edge, corner, etc. The coefficients of the expansion, therefore, can be thought of as dense local features, estimating at each point the degree of presence of, for example, a horizontal edge, a corner with contrast of a certain type, etc. These coefficients are normalized and used as digits in a chosen number system which allows one to create a unique number for each type of local structure. The choice of the basis of the number system allows one to give different emphasis to different types of local feature (e.g., corners versus edges), and, thus, the method we present forms a unified framework in terms of which several feature matching methods may be interpreted. The algorithm is compared with wavelet and contour based approaches, using simulated and real images. The two images are assumed to differ from each other by a rotation and a translation only.

Three-dimensional nonlinear invisible boundary detection.

The human vision system can discriminate regions which differ up to the second-order statistics only. We present an algorithm designed to reveal "hidden" boundaries in gray level images, by computing gradients in higher order statistics of the data. We demonstrate it by applying it to the identification of possible "hidden" boundaries of glioblastomas as manifest themselves in three-dimensional (3-D) MRI scans, using a model driven approach. We also demonstrate the method using a nonmodel driven approach where we have no prior information about the location of possible boundaries. In this case, we use 3-D MRI data concerning schizophrenic patients and normal controls.

Detection of structural differences between the brains of schizophrenic patients and controls.

This paper investigates the validity of the null hypothesis: there are no structural differences between the brains of schizophrenic and normal control subjects that manifest themselves in MRI-T(2) data and distinguish the two populations in a statistically significant way. The data used refer to 21 schizophrenic patients and 19 normal controls, matched for age, sex and social background. The methodology used is based on three-dimensional texture analysis, which is used to quantify anisotropy in the data at scales of the order of a few millimetres. These data reject the null hypothesis. In addition, this article attempts to identify the regions of the brain that are responsible for the morphological characteristics that distinguish the two populations. For this purpose, it utilises a second texture analysis method that, in spite of being a global method, allows one to trace back to the data the origin of the features that most distinctly distinguish the two populations. This method indicates that the features that distinguish the two populations with P values smaller than 10(-6) are located in the most inferior part of the brain and in particular in the tissue that makes up the sulci. It is stressed that in order to preserve the integrity of the data for texture calculations, no registration of anatomical structures is performed, and the most inferior part of the brain is identified as referring to those slices of the scans that visually correspond to slices 1-12 of the Talairach and Tournoux brain atlas.

Affine invariant features from the trace transform.

The trace transform is a generalization of the Radon transform that allows one to construct image features that are invariant to a chosen group of image transformations. In this paper, we propose a methodology and appropriate functionals that can be computed from the image function and which can be used to calculate features invariant to the group of affine transforms. We demonstrate the usefulness of the constructed image descriptors in retrieving images from an image database and compare it with relevant state-of-the-art object retrieval methods.

Guest editorial: Introduction to the special issue on modern control for computer games.

A typical gaming scenario, as developed in the past 20 years, involves a player interacting with a game using a specialized input device, such as a joystic, a mouse, a keyboard, etc. Recent technological advances and new sensors (for example, low cost commodity depth cameras) have enabled the introduction of more elaborated approaches in which the player is now able to interact with the game using his body pose, facial expressions, actions, and even his physiological signals. A new era of games has already started, employing computer vision techniques, brain-computer interfaces systems, haptic and wearable devices. The future lies in games that will be intelligent enough not only to extract the player's commands provided by his speech and gestures but also his behavioral cues, as well as his/her emotional states, and adjust their game plot accordingly in order to ensure more realistic and satisfactory gameplay experience. This special issue on modern control for computer games discusses several interdisciplinary factors that influence a user's input to a game, something directly linked to the gaming experience. These include, but are not limited to, the following: behavioral affective gaming, user satisfaction and perception, motion capture and scene modeling, and complete software frameworks that address several challenges risen in such scenarios.

Regularized kernel discriminant analysis with a robust kernel for face recognition and verification.

We propose a robust approach to discriminant kernel-based feature extraction for face recognition and verification. We show, for the first time, how to perform the eigen analysis of the within-class scatter matrix directly in the feature space. This eigen analysis provides the eigenspectrum of its range space and the corresponding eigenvectors as well as the eigenvectors spanning its null space. Based on our analysis, we propose a kernel discriminant analysis (KDA) which combines eigenspectrum regularization with a feature-level scheme (ER-KDA). Finally, we combine the proposed ER-KDA with a nonlinear robust kernel particularly suitable for face recognition/verification applications which require robustness against outliers caused by occlusions and illumination changes. We applied the proposed framework to several popular databases (Yale, AR, XM2VTS) and achieved state-of-the-art performance for most of our experiments.

Nonlinear non-negative component analysis algorithms.

In this paper, general solutions for nonlinear non-negative component analysis for data representation and recognition are proposed. Motivated by a combination of the non-negative matrix factorization (NMF) algorithm and kernel theory, which has lead to a recently proposed NMF algorithm in a polynomial feature space, we propose a general framework where one can build a nonlinear non-negative component analysis method using kernels, the so-called projected gradient kernel non-negative matrix factorization (PGKNMF). In the proposed approach, arbitrary positive definite kernels can be adopted while at the same time it is ensured that the limit point of the procedure is a stationary point of the optimization problem. Moreover, we propose fixed point algorithms for the special case of Gaussian radial basis function (RBF) kernels. We demonstrate the power of the proposed methods in face and facial expression recognition applications.

Cephalometric landmarks identification using probabilistic relaxation.

In this paper, we develop methodology to locate cephalometric landmarks on X-ray images based on probabilistic relaxation, which combines local contextual information from the general shape of the bones of the head (used as measurements specific to each landmark in the form of its shape context) and relational information, expressing the relative position of the landmarks with respect to each other.

Attentional vs computational complexity measures in observing paintings.

Because of the great heterogeneity of subjects and styles, esthetic perception delineates a special and elusive field of research in vision, which represents an interesting challenge for cognitive science tools. With specific regard to the role of visual complexity, in this paper we present an experiment aimed to measure this dimension in a heterogeneous set of paintings. We compared perceived time complexity measures - based on a temporal estimation paradigm - with physical and statistical properties of the paintings, obtaining a strong correlation between psychological and computational results.

Automatic extraction of local axis of bone symmetry in CT images.

We present an algorithm that extracts local axis of symmetry in CT images automatically. The proposed method combines registration and extraction of bone contours to generate the desired symmetry axis. The method consists of several stages: first extracting the bone contours of the images by using an active contour method, then finding grossly an axis that allows the division of the image into two parts, loosely called 'half' images, but with the understanding that they are not exactly the two halves of the image but rather the two halves of the depicted object. After that, finding a mapping that aligns the first half of the image with the second half and finally, finding the local axis of symmetry from corresponding contours.

Performance prediction using EEG and trial-invariant characteristic signals.

One of the most important parts of all applications trying to discriminate between a person's different mental tasks using their recorded EEG data is the process of feature construction. A common practice for this is to exploit an apriori knowledge about the nature of the mental processes of interest and their impact on the EEG signals. However, the use of features constructed in this way is restricted to applications concerning the corresponding mental processes. We present here a novel method for EEG data classification which is very general as it makes no assumptions about the nature of the EEG signals. It is based on the construction of a characteristic signal for each class which remains as invariant as possible over the trials belonging to that class. We use the proposed method in combination with a novel method for channel selection in an oddball experiment to predict a person's quick or late response.

Improved 2-D vector field reconstruction using virtual sensors and the Radon transform.

This paper describes a method that allows one to recover both components of a 2-D vector field based on boundary information only, by solving a system of linear equations. The analysis is carried out in the digital domain and takes advantage of the redundancy in the boundary data, since these may be viewed as weighted sums of the local vector field's Cartesian components. Furthermore, a sampling of lines is used in order to combine the available measurements along continuous tracing lines with the digitised 2-D space where the solution is sought. A significant enhancement in the performance of the proposed algorithm is achieved by using, apart from real data, also boundary data obtained at virtual sensors. The potential of the proposed method is demonstrated by presenting an example of vector field reconstruction.

Axon tracing in the adult rat optic nerve and tract after intravitreal injection of MnDPDP using a semiautomatic segmentation technique.

PURPOSE: To develop and validate an objective technique for 3D segmentation of manganese-enhanced MR images of the optic nerve/tract (ON) in adult rats to improve contrast-to-noise (CNR) calculations and use the technique to ascertain if manganese dipyridoxyl diphosphate (MnDPDP) gives sufficient Mn(2+) enhancement compared to MnCl(2) when used for functional imaging of the visual pathway. MATERIALS AND METHODS: Intravitreous injection of the manganese-releasing MR contrast agent MnDPDP (30 nmol Mn(2+)) was performed to trace the ON in adult rats (n = 4). A positive control group of rats (n = 5) received a standard preparation of MnCl(2) (200 nmol Mn(2+)), while gadodiamide (1500 nmol Gd(3+)) was administered in negative control rats (n = 2). An objective technique for 3D segmentation of the enhanced ON was developed. CNR profiles along the ON were calculated by resampling the 3D image-volume in 2D planes perpendicular to the Mn(2+) enhanced ON in 0.2 mm steps, 4 mm along the segmented ON measured from the lamina cribrosa. RESULTS: The ON was successfully segmented and CNR calculated accurately within 2 minutes in a representative 3D MR image volume. Intravitreal MnDPDP injection resulted in significant MRI contrast enhancement of the retina and ON after 12-24 hours similar to that of MnCl(2) injection. CONCLUSION: 3D semiautomated image segmentation and the use of MnDPDP can improve in vivo axon tracing based on MRI. Mn(2+) was found to be released from MnDPDP after intravitreal injection in sufficient amounts to obtain functional tracing of the adult rat primary visual pathway.