Fundamental problems in electrophysiology can be studied by computationally modeling and simulating the associated microscopic and macroscopic bioelectric fields. To study such fields computationally, researchers have developed a number of numerical and computational techniques. Advances in computer architectures have allowed researchers to model increasingly complex biophysical system. Modeling such systems requires a researcher to apply a wide variety of computational and numerical methods to describe the underlying physics and physiology of the associated three-dimensional geometries. Issues naturally arise as to the accuracy and efficiency of such methods. In this paper we review computational and numerical methods for solving bioelectric field problems. The motivating applications represent a class of bioelectric field problems that arise in electrocardiography and

The noise usually produces a non-linear distortion of the feature space considered for Automatic Speech Recognition. This distortion causes a mismatch between the training and recognition conditions which significantly degrades the performance of speech recognizers. In this contribution we analyze the effect of the additive noise over cepstral based representations and we compare several approaches to compensate this effect. We discuss the importance of the non-linearities introduced by the noise and we propose a method (based on the histogram equalization technique) specifically oriented to the compensation of the non-linear transformation caused by the additive noise. The proposed method has been evaluated using the AURORA-2 database and task. The recognition results show significant improvements with respect to other compensation methods reported in the bibliography and reveals the importance of the non-linear effects of the noise and the utility of the proposed method.

Considering the fact that most of the multimedia database systems include querying by object features, a novel approach for color and shape querying and retrieval is proposed. The approach is histogram-based and it is supported by an auxiliary object extraction tool in the query-by-feature component of a multimedia database system. The object extraction tool is semi-automatic, hence it can successfully capture salient object regions for most of the images and/or video frames. The use of the object extraction tool facilitates object-based querying of color and shape content. In the histogram-based approach, the color and shape can be integrated to improve the performance of querying. It is shown through performance experiments that the histogram-based approach overcomes the deficiencies of the existing methods for querying by shape. The evaluation of the effectiveness and the robustness of the histogram-based approach is also presented via performance experiments.

Humans use gestures in most communicative acts. How are these gestures initiated and performed? What kinds of communicative roles do they play and what kinds of meanings do they convey? How do listeners extract and understand these meanings? Will it be possible to build computerized communicating agents that can extract and understand the meanings and accordingly simulate and display expressive gestures on the computer in such a way that they can be effective conversational partners? All these questions are easy to ask, but far more difficult to answer. In the thesis we try to address these questions regarding the synthesis and acquisition of communicative gestures. Our approach to gesture is...

The noise degrades the performance of Automatic Speech Recognition systems mainly due to the mismatch between the training and recognition conditions it introduces. The noise causes a distortion of the feature space which usually presents a non-linear behavior. In order to reduce this mismatch, the methods proposed for robust speech recognition try to compensate the noise effect either by obtaining an estimation of the clean speech or by adapting the recognizer acoustic models for a proper modeling of the noisy speech. In this paper we propose a method to compensate the noise effect over the speech representation. This method is based on the histogram equalization technique frequently applied for Digital Image Processing, which has been adapted to the speech representation. For each component of the feature vectors representing the speech signal, the histogram is estimated and the transformation which converts it into a reference histogram is calculated. Such transformations tend to compensate the distortion the noise produces over the different components of the feature vector and improve the performance of the recognition systems under noise conditions. We describe how the histogram equalization method can be adapted to robust speech recognition and present some recognition experiments to evaluate the proposed method.

An improved method for deformable shape-based image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. The quality of a candidate region merging is evaluated by a cost measure that includes: homogeneity of image properties within the combined region, degree of overlap with a deformed shape model, and a deformation likelihood term. Perceptually-motivated criteria are used to determine where/how to split regions, based on the local shape properties of the region group's bounding contour. A globally consistent interpretation is determined in part by the minimum description length principle. Experiments show that the model-based splitting strategy yields a significant improvement in segmention over a method that uses merging alone. 1 Introduction Retrieval by shape is a key topic in content-based image retrieval research. Unfortunately, retrieval...

Most pathologies (tumor, bleed, stroke) of the human brain can be determined by a symmetry-based analysis of neural scans showing the brain's 3D internal structure. Detecting departures of this internal structure from its normal bilateral symmetry can guide the classification of abnormalities. This process is facilitated by first locating the ideal symmetry plane (midsagittal) with respect to which the brain is invariant under reflection. An algorithm to automatically identify this bilateral symmetry plane from a given 3D clinical image has been developed. The method has been tested on both normal and pathological brain scans, multimodal data (CT and MR), and on coarsely sliced samples with elongated voxel sizes. Keywords: bilateral symmetry, midsagittal plane, cross-correlation 1. INTRODUCTION Normal human brains present an approximate bilateral symmetry with respect to their midsagittal planes, this symmetry is often absent in pathological brains. Most pathologies (tumor, bleed, st...

Image segmentation is an important processing step in many image, video and computer vision applications. Extensive research has been done in creating many different approaches and algorithms for image segmentation, but it is still difficult to assess whether one algorithm produces more accurate segmentations than another, whether it be for a particular image or set of images, or more generally, for a whole class of images. To date, the most common method for evaluating the effectiveness of a segmentation method is subjective evaluation, in which a human visually compares the image segmentation results for separate segmentation algorithms, which is a tedious process and inherently limits the depth of evaluation to a relatively small number of segmentation comparisons over a predetermined set of images. Another common evaluation alternative is supervised evaluation, in which a segmented image is compared against a manually-segmented or pre-processed reference image. Evaluation methods that require user assistance, such as subjective evaluation and supervised evaluation, are infeasible in many vision applications, so unsupervised methods are necessary. Unsupervised evaluation enables the objective comparison of both different segmentation methods and different parameterizations of a single method, without requiring human visual comparisons or comparison with a manually-segmented or pre-processed reference image. Additionally, unsupervised methods generate results for individual images and images whose characteristics

Abstract not found

Abstract not found