Felix Calderon

An Accurate and Efficient Bayesian Method for Automatic Segmentation of Brain MRI

Automatic 3D segmentation of the brain from MR scans is a challenging problem that has received enormous amount of attention lately. Of the techniques reported in literature, very few are fully automatic. In this paper, we present an efficient and accurate, fully automatic 3D segmentation procedure for brain MR scans. It has several salient features namely, (1) instead of a single multiplicative bias field that affects all tissue intensities, separate parametric smooth models are used for the intensity of each class. This may be a more realistic model and avoids the need for a logarithmic transformation. (2) A brain atlas is used in conjunction with a robust registration procedure to find a non-rigid transformation that maps the standard brain to the specimen to be segmented. This transformation is then used to: segment the brain from non-brain tissue; compute prior probabilities for each class at each voxel location and find an appropriate automatic initialization. (3) Finally, a novel algorithm is presented which is a variant of the EM procedure, that incorporates a fast and accurate way to find optimal segmentations, given the intensity models along with the spatial coherence assumption. Experimental results with both synthetic and real data are included, as well as comparisons of the performance of our algorithm with that of other published methods.

Solving a School Timetabling Problem Using a Bee Algorithm

The timetabling problem consists in fixing a sequence of meetings between teachers and students in a given period of time, satisfying a set of different constraints. This paper shows the implementation of a Bee Algorithm (BA) to solve the Scholar Timetabling Problem. In the implemented BA, scout bees find feasible solutions while collector bees search in their neighborhood to find better solutions. While other algorithms evaluate every plausible assignment, the implemented algorithm only evaluates feasible solutions. This approach seems to be helpful to manage constrained problems. We propose a new measurement for replacing population that considers the evolutionary history of the bees as well as their fitness. Experimental results are presented for two real schools, where the algorithm shows promising results.

A Robust Iterative Closest Point Algorithm with Augmented Features

The Iterative Closest Point (ICP) is widely used for 2D - 3D alignment when an initial estimate of the relative pose is known. Many ICP variants have been proposed, affecting all phases of the algorithm from the point selection and matching to the minimization strategy. This paper presents a method for 2D laser scan matching that modifies the matching phase. In the first stage of the matching phase our method follows the ordinary association strategy: for each point of the new-scan it finds the closest point in the reference-scan. In a second stage, the most probable normal vector difference is calculated and associations that do not fulfill the normal vector difference requirement are re-associated by finding a better association in the neighborhood. This matching strategy improves the ICP performance specially when the initial estimate is not close to the right one, as it is shown in the simulated and real tests.

Surface-normal estimation with neighborhood reorganization for 3D reconstruction

Fastest three-dimensional (3D) surface reconstruction algorithms, from point clouds, require of the knowledge of the surface-normals. The accuracy, of state of the art methods, depends on the precision of estimated surface-normals. Surface-normals are estimated by assuming that the surface can be locally modelled by a plane as was proposed by Hoppe et. al [1]. Thus, current methods for estimating surface-normals are prone to introduce artifacts at the geometric edges or corners of the objects. In this paper an algorithm for Normal Estimation with Neighborhood Reorganization (NENR) is presented. Our proposal changes the characteristics of the neighborhood in places with corners or edges by assuming a locally plane piecewise surface. The results obtained by NENR improve the quality of the normal with respect to the state of the art algorithms. The new neighborhood computed by NENR, use only those points that belong to the same plane and they are the nearest neighbors. Experiments in synthetic and real data shown an improvement on the geometric edges of 3D reconstructed surfaces when our algorithm is used.

A Tutorial on Parametric Image Registration

1. Resume This chapter introduces the reader to the area of parametric image registration, from a beginner’s point of view. Given a model, an input image and a reference image, the parametric registration task is to find a set of parameters (of the model) that transform the input image into the reference image. This chapter reviews models of the general projective, affine, similarity and Euclidean transformations of images, and develop a full example for affine and projective transformation. It also describes two new methods of computing the set of image derivatives needed, besides the classical method reported in the literature. The new methods for computing derivatives are faster and more accurate than the classical method.

The MPM-MAP algorithm for image segmentation

We present a new algorithm for the efficient estimation of piecewise parametric models for image segmentation. This algorithm permits the simultaneous estimation of: the number of models; the parameters for each model and the regions where each model is applicable. It is based on Bayesian estimation theory, and is theoretically justified by the use of a specific cost function that decreases at every iteration and by a new model for the posterior marginal distributions which is amenable to the use of fast computational methods.

Evolutionary computation solutions to the circle packing problem

In this work, we present an evolutionary omputation-based solution to the circle packing problem (ECPP). The circle packing problem consists of placing a set of circles into a larger containing circle without overlaps: a problem known to be NP-hard. Given the impossibility to solve this problem efficiently, traditional and heuristic methods have been proposed to solve it. A naïve representation for chromosomes in a population-based heuristic search leads to high probabilities of violation of the problem constraints, i.e., overlapping. To convert solutions that violate constraints into ones that do not (i.e., feasible solutions), in this paper we propose two repair mechanisms. The first one considers every circle as an elastic ring and overlaps create repulsion forces that lead the circles to positions where the overlaps are resolved. The second one forms a Delaunay triangulation with the circle centers and repairs the circles in each triangle at a time, making sure repaired triangles are not modified later on. Based on the proposed repair heuristics, we present the results of the solution to the CPP problem to a set of unit circle problems (whose exact optimal solutions are known). These benchmark problems are solved using genetic algorithms, evolutionary strategies, particle swarm optimization, and differential evolution. The performance of the solutions is compared to those known solutions based on the packing density. We then perform a series of experiments to determine the performance of ECPP with non-unitary circles. First, we compare ECPP’s results to those of a public competition, which stand as the world record for that particular instance of the non-unitary CPP. On a second set of experiments, we control the variance of the size of the circles. In all experiments, ECPP yields satisfactory near-optimal solutions.

The MPM-MAP algorithm for motion segmentation

We present an MPM-MAP application for the efficient estimation of piecewise parametric models for motion segmentation. This algorithm permits the simultaneous estimation of: the number of models, the parameters for each model and the regions where each model is applicable. It is based on Bayesian estimation theory, and is theoretically justified by the use of a specific cost function whose expected value decreases at every iteration and by a new model for the posterior marginal distributions which is amenable to the use of fast computational methods. We compare the performance of this method with the most similar segmentation algorithm, the well known Expectation-Maximization algorithm. We present a comparison of the performance of both algorithms using synthetic and real image sequences.

A Constraint-Handling Genetic Algorithm to Power Economic Dispatch

This paper presents a new constraint-handling genetic approach for solving the economic dispatch problem in electric power systems. A real code genetic algorithm is implemented to minimize the active power generation cost while satisfying power balance (energy conservation) and generation limit constraints simultaneously during the optimization process. This is achieved by introducing a novel strategy for searching the solution on the energy conservative space, producing only individuals that fulfill the energy conservation constraint, and reducing the search space in one dimension. Computer simulations on three benchmark electrical systems show the prowess of the proposed approach whose results are very close to those reported by other authors using different methods.

Robust Parametric Image Registration

We present a hybrid method to perform parametric image registration. The objective is to find the best set of parameters to match a transformed image (possible with noise) to a target image. Hybridization occurs when Genetic Algorithms are able to determine rough areas of the parameter optimization space, but fail to produce fine tunings for those parameters. In that case, the Newton– Levenberg–Marquardt method is used to refine results. Another important combination of techniques results when we want to compare noisy images. In this case, the fitness function needs to be robust enough to discard misleading information contained in outliers. Statistical techniques are employed in this case to be able to compare images in the presence of noise. The resulting implementation, called GA–SSD–ARC–NLM was compared against robust registration methods used in the area of image processing. GA–SSD–ARC–NLM outperforms the RANSAC and the Lorentzian Estimator methods when images are noisy o they include occluded parts from objects, or even when new objects are on the target images.