The aim of this study has been to develop a method to indicate the similar sequences of electroencephalographic (EEG) maps in a series. A method for the analysis of sequence similarity using the matrix of correlation coefficients for each pair of the EEG maps in the series has been proposed. The results for two series of EEG maps for seizure activity episodes and for activity before, during and after the seizure episode are presented. Analysis of images of the correlation coefficients matrices has allowed us to determine the characteristic features of the areas in these matrices corresponding to the assumed similarity relations, and to indicate the sequences fulfilling these relationships.
We address in this paper the problem of particle-based simulation of breaking waves. We present a new set of equations based on oceanographic research which allow us to deal with several types of breaking waves and multiple wave trains with full control over governing parameters. In order to reduce computations in non-significant areas, we also describe a simple and efficient multiresolution scheme, controlled using the properties of our breaking wave model.
In the paper we present an innovative computer vision based rail crossing protection system. A camera installed on top of a mast overlooking the crossing continuously monitors the scene, searching for objects that have stopped on the rail tracks. The system is designed to transmit images of the incident to the approaching trains as soon as any conflictive object has been detected. A simple user interface on board of the train displays the image sequence with a graphical aid clearly identifying the offending object in the image. In that way, train drivers are alerted of the presence of possible obstacles well before the train has approached the crossing. The system we describe operates autonomously for long periods of time without human intervention and adapts automatically to the changing environmental conditions. Several innovations, designed to deal with the above circumstances, are proposed in the paper, including: an adaptive segmentation algorithm, an innovative method for the detection of stopped objects and differentiated approaches for day and night processing.
The detection of moving objects in video streams is generally performed by analysis of the differences between the modelled background and the current stream content, by matching object models, extracting and clustering the features of objects or else by using various filtering methods. Filtering is performed on the transformed contents of the video stream. Due to implementational constraints, mainly limited processing resources, solutions based on these principles of detection are sensitive to ambient light variations, objects shadows and camera movement. This paper presents a method for the detection of moving objects that uses a data reduction technique based on wavelets. Instead of the analysis of raw video data, wavelet coefficients of an appropriate scale are explored. In order to satisfy low processing requirements, an integer version of discrete wavelet transform is chosen for processing. To facilitate the detection, each frame is converted into a vector of pixel values. Consecutive video vectors are transformed using one-dimensional Discrete Wave Transform (DWT). The computed DWT coefficients make up a surface, which maps changes in their values over time. The surface is analysed to find clusters of values corresponding to moving objects. The checked patches represent moving objects. The width of a patch indicates the object size. Background details and illumination changes are represented by gradually changing patterns. Various examples demonstrate the potential of the method for practical applications.
Stereovision is a passive technique for estimation of depth in 3D scenes. Unfortunately, depth estimation in this imaging technique is computationally demanding. We show that stereovision matching algorithms can be efficiently mapped onto the present-day graphics processing units (GPUs). A number of modifications to the original image disparity estimation algorithm have been proposed that make running its computation on GPU platforms particularly efficient. A complete depth estimation system was implemented in GPU, covering correction of camera distortions, image rectification and disparity estimation. To obtain modularity of developed software, the DirectShow multimedia technology was used. Examples, computed depth maps are shown, and time performances of the proposed algorithms are outlined. The developed system has proved the usefulness of both GPU implementation and the DirectShow technology in scene depth estimation.
In this paper we developed an efficient optimal robust watermarking technique using genetic algorithm (GA) for images of Indian historical monuments and their corresponding names. The watermarks are embedded into the HL and LH frequency coefficients in the Haar wavelet transform domain. Since the embedding technique is blind, it does not require the original image in the watermark extraction. We also develop an optimization technique using the GA to search for the optimal locations in order to improve both quality of watermarked image and robustness of the watermark. We analyze the performance of the proposed watermarking technique in terms of peak signal-to-noise ratio (PSNR) and normalized correlation (NC). The experimental and the comparative results show that the proposed technique can achieve a good robustness against most of the attacks which are included in this study. For typical image quality, the proposed technique outperforms the existing one with a PSNR of 36 dB and the NC value of 0.96.
Computerised monitoring of CCTV images is attracting a lot of attention both from potential end-users seeking to increase the effectiveness of their video surveillance systems and as a popular research topic as new methods and algorithms are being developed. In this paper an approach to detecting knives in images is presented. It is based on the use of Histograms of Oriented Gradients (HOG), feature descriptors invariant to geometric and photometric transformations except for rotation. We introduce a dataset containing images of knives in different backgrounds and in varying lighting conditions and evaluate the performance of an HOG-based SVM classifier. We study the question of creating a detector based on knife blade colour and discuss the use of GPU parallel computing as a method of speeding up the detection process.
Modelling three-dimensional shapes plays an increasingly significant role in modern computer graphics. Geometry synthesis is used in many fields, including digital cinema, electronic entertainment and computer simulations. Unfortunately, the modelling process is still done manually, offering a unique output at the cost of tedious work. There is a constant need to replace designers' work with intelligent automated algorithms. The methods based on the automation of modelling processes offer a variety of three-dimensional structures within limited time and restricted money budget. This paper addresses the problem of automated modelling of virtual structures such as caves, buildings and clouds, and presents an alternative solution in the form of a hybrid system. The innovative approach combines two independent methods well known in three-dimensional computer graphics: shape grammar and shape morphing. In the modelling process, it is possible to obtain the characteristics of 3D structures with non-spherical mesh topology. The objects and their transformations are described by functions, while rule grammars define the geometry modelling process. The shapes thus obtained can be freely deformed in the subsequent rules. The resulting structure can be rendered up to very high levels of visual realism. However, in the paper we present the description of the algorithm illustrated by results on a 3D mesh without focusing on photorealistic rendering aspects. We also propose some measures that can be used to verify the model geometry.
This paper develops a face detection method in color images using a multi-layer Neural Network classification. The proposed method is based on two image processing steps which first detect skin regions in the color image and then extract face information from those regions. Instead of performing huge search in every part of the test images, a pre-processing method for candidate face regions guides the image search using neural networks. The new algorithms perform fast and accurate face detection. Experiments have been carried out and satisfactory results have been obtained which indicate the robustness of the first process to detect faces under different environmental conditions.
Image segmentation is a fundamental process employed in many applications of pattern recognition, video analysis, computer vision and image understanding in order to allow further image content exploitation in an efficient way. It is often used to partition an image into separate regions. As recent trends in image segmentation show, the use of artificial and/or computational intelligence (AI and/or CI) techniques has become more popular as an alternative to the conventional techniques. In this paper, we present an extensive and comprehensive review of the image processing area for advanced researchers. This study introduces the theoretical fundamentals of image segmentation using AI and/or CI techniques based on fuzzy logic (FL), genetic algorithm (GA) and artificial neural networks (ANN). Besides, this snrvey examines the applications of these techniques in different image segmentation areas. In the literature, these techniques are used as an interpretation tool for segmentation. In our study, these tools are focused on because of their capabilities, such as robnstness, segmentation accuracy and low computational costs. Moreover, we review 56 remarkable studies from the last decade (i.e., the years between 2001 and 2010), which involve different image segmentation approaches using FL, GAs, ANNs and hybrid intelligent systems (HISs). In our state-of-the-art survey, the comparison of the reviewed papers in related categories is made based on both the corresponding properties of segmentation as well as performance evaluation of the related method proposed in a given reviewed paper. The results and recent trends are also discussed.
Two constructions of surfaces filling polygonal holes in piecewise B-spline bicubic surfaces with tangent plane continuity are described. The filling surfaces are obtained by minimization of functionals which impose penalty on curvature discontinuities. One of the functionals is a quadratic form, while the other functional is defined with a parameterization-independent formula. The resulting surfaces may be used instead of class G2 surfaces in practical applications; the penalty approach enables simplification of the construction, and reduction in the degree of patches filling the hole from (9,9) to (5,5) without any visible quality degradation. The notion of class Gn quasi Gm surfaces, i.e. class Gn surfaces optimized to approximate class Gm surfaces, is proposed.
Two alternatives to the standard (central differencing) method for estimating normals of Marching Cubes isosurfaces are considered. The methods are based on higher order approximations of dataset gradients. Of primary concern here are the effects of these methods on rendering quality, which is evaluated here through pixel-by-pixel comparisons of typical-fidelity isosurfaces versus high-fidelity rendering achievable from analytically derived formulae. The evaluations also consider effects of noise on isosurface rendering quality for renderings based on standard versus higher order gradients.
This paper presents an algorithm used to improve the effectiveness of early prostate cancer (PCa) detection. The necessity for using such a computational method lies in the fact that although perfusion computed tomography (p-CT) is considered a good technique for the detection of early PCa, the p-CT prostate images are very difficult to interpret manually by radiologists. We hereby propose a methodology for computational analysis of p-CT prostate images based on textural coefficients derived from co-occurrence matrices and their 21 coefficients. The selection of only a few of the considered features ensures the necessary balance between matching set of already known images and new, not yet clear cases. The proposed algorithm for automatic differentiation of the healthy area of the image from the cancerous region was tested on a set of 59 prostate images. Although the results were not entirely satisfactory (86% correct recognitions), this method may be considered as the base for the development of a better algorithm.
This paper presents a hidden Markov model-based online handwritten character recognition for Gurmukhi script. We discuss a procedure to develop a hidden Markov model database in order to recognize Gurmukhi characters. A test with 60 handwritten samples, where each sample includes 41 Gurmukhi characters, shows a 91.95% recognition rate, and an average recognition speed of 0.112 seconds per stroke. The hidden Markov model database has been developed in XML using 5330 Gurmukhi characters. This work shall be useful to implement a hidden Markov model in online handwriting recognition and its software development.
The paper presents the diagnostics of parenchyma echogenicity and organ dimensions in thyroid examinations in case of the Hashimoto's disease using image processing methods. In case of discovering focal changes within the thyroid, a method for their pathology evaluation is suggested. The detector proposed operates fully automatically; using the information on the image texture it detects an artery in the image, which plays the role of a reference point, and based on it - detects the area of interest.
Over the recent years, the image sensor technology has provided tools for wide-angle and high-resolution 3D recording, analysis and modeling of static or dynamic scenes, ranging from small objects, such as artifacts in a museum, to large-scale 3D models of castles or 3D city maps, also allowing real time 3D data acquisition from a moving platform, e.g. in vision-based driver assistance. More recently, due to the rapidly evolving and improving stereoscopic display technology, many of these panoramic image applications have started to contribute to stereo visualization, thus increasing realistic and immersive appearances. This paper introduces a methodology for stereo panorama acquisition and provides detailed technologies of mapping between different forms of panoramic images. Image examples illustrate the potential for projects in arts, science and technology.
Object recognition is considered to be a predominant basic issue in computer vision. It is a challenging issue against inconsistent illumination, partial occlusion, changing background and shifting viewpoint, because considerable variations are exhibited by diversified real world patterns. The virtue of feature fusion lies in its reliability and capability for object recognition in terms of actual redundancy and complementary information. In this paper, we have developed an efficient hybrid approach using scale invariant features and machine learning techniques for object recognition. We extract the scale invariant features, namely color, shape and texture of the objects, separately with tile aid of suitable feature extraction techniques. Then, we integrate the color, shape and texture features of tile objects at the feature level, so as to improve the recognition performance. The fused feature set serves as a pattern for the forthcoming processes involved in the developed approach. Subsequently, we hybridize the process of object recognition by combining the pattern recognition algorithms like Support Vector Machine, Discriminant Canonical Correlation, and Locality Preserving Projections. Obviously, with three different pattern recognition algorithms employed, we are likely to get three distinct or identical results enumbered with false positives. So in order to reduce the number of false positives, we devise a decision module based on Neural Networks that takes in the match percentage from the chosen pattern recognition algorithms, and then decides the recognition result based on those match values. Our approach is evaluated on the Amsterdam Library of Object Images collection, a large collection of object images containing 1000 objects recorded under various imaging circumstances. The experimental results clearly demonstrate that our approach significantly outperforms the state-of-the-art methods for combining color, shape and texture features. The developed method is shown to be effective under a wide variety of imaging conditions. Finally, we employ empirical evaluation to evaluate our approach with the aid of an accuracy estimation method, such as k-fold cross validation.
In surface construction, existing marching cubes (MC) methods require sample values at cell vertices to be non-zero after thresholding, or modify them otherwise. The modification may introduce problems in the constructed surface, such as topological changes, representation errors, and preference for positive or negative values. This paper presents a generalized MC algorithm. It constructs surface patches by exploiting cycles in cells without changing the sample values at vertices, and thus allows cell vertices with zero sample values to lie on the constructed surface. The simulation results show that the proposed Zero-Crossing MC method preserves better topologies of implicit surfaces that pass through cell vertices, and represents the surfaces more accurately. Its efficiency is comparable to existing MC methods in constructing surfaces.
This paper presents a novel method for digital image segmentation based on the analogy between streamlines in fluid dynamics and isophote lines in digital images. The segmentation problem is reformulated so that the image intensity corresponds to the stream function for a two-dimensional, incompressible flow, and image intensity gradients are represented as the fluid velocity vector. Segmentation is effected by computing the streamlines by solving a coupled system of ordinary differential equations using a fourth-order Runge-Kutta method. Selection of the initial starting point for segmentation is based on color homogeneity in terms of local color gradient, and on variance. The effectiveness of the developed segmentation method is demonstrated through a number of case studies, ranging from gray level to colored images.
