Bohou Xu¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.11, No.4, pp. 97-98, 2009, DOI:10.3970/icces.2009.011.097

Abstract Stochastic resonance is a mechanical concept and may be used to image processing. This paper aims to develop an elementary theory of two-dimensional parameter-induced stochastic resonance (PSR) in order to contribute a new approach to nonlinear image processing. For tackling applications of stochastic resonance (SR) in image processing where adding noise may not be an easy task, we propose to generalize the concept of parameter-induced stochastic resonance from the one-dimensional case to the two-dimensional case. Specially, a novel two-dimensional system which demonstrates the feature of parameter-induced stochastic resonance is proposed for nonlinear image processing. An… More >

Jeng-Tzong Chen^1,2, S. C. Shieh¹, Y. T. Lee¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.11, No.4, pp. 95-96, 2009, DOI:10.3970/icces.2009.011.095

Abstract Green's functions of Laplace problems with circular boundaries are solved by using three approaches, analytical, semi-analytical and numerical solutions. For the analytical solution, we derive the Green's function by using the bipolar coordinates. Three kinds of semi-analytical solutions using (a). image method, (b). the null field BIE using the Green's third identity, and (c). the null field BIE in conjunction with superposition technique using the addition theorem are considered. A numerical method using the image concept is also employed to study the optimal location of MFS. It is interesting to find that the two frozen More >

P. Ruzicka¹, P. Bendova¹, S. Konvickova¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.10, No.3, pp. 91-96, 2009, DOI:10.3970/icces.2009.010.091

Abstract The objective of the study was to prove magnetic resonance imaging as suitable instrument for exploring the nature and amplitude of displacements within the bony pelvis induced by asymmetrically altered pelvic floor muscle characteristics. Repeated MR imaging of 14 females was performed. Spatial coordinates of 23 pelvic landmarks were localized in each subject and registered by interactive and automatic procedures. Modalities of registration procedure were tested and compared by the precision of registration. The software tool was developed to perform registrations and data analyses including individual registration error evaluation. The automatic registration with vertebra L5 More >

Maria João M. Vasconcelos¹, João Manuel R. S. Tavares¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.10, No.1, pp. 3-4, 2009, DOI:10.3970/icces.2009.010.003

Abstract In the last years, researchers from the Computational Vision working field have been developing new methods to perform image segmentation for human motion analysis. The development of computational techniques suitable to automatically identify the structures involved is necessary to obtain more representative and robust features to be further used in the analysis of human motion from image sequences.
The first step of human motion analysis from image sequences is strongly related with image segmentation. In fact, the first goal of any system designed for this aim is the identification of the structures’ features to be analysed… More >

Chowhan S.S.¹, G.N. Shinde²

The International Conference on Computational & Experimental Engineering and Sciences, Vol.9, No.1, pp. 67-74, 2009, DOI:10.3970/icces.2009.009.067

Abstract Feature selection, often used as a pre-processing step to machine learning, is designed to reduce dimensionality, eliminate irrelevant data and improve accuracy. Iris Basis is our first attempt to reduce the dimensionality of the problem while focusing only on parts of the scene that effectively identify the individual. Independent Component Analysis (ICA) is to extract iris feature to recognize iris pattern. Principal Component Analysis (PCA) is a dimension-reduction tool that can be used to reduce a large set of variables to a small set that still contains most of the information in the large set. More >

Victor Hugo Costa de Albuquerque¹, Tarique da Silvira Cavalcante², Pedro Pedrosa Rebouças Filho², João Manuel R. S. Tavares¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.9, No.1, pp. 23-24, 2009, DOI:10.3970/icces.2009.009.023

Abstract Mechanical tests for measurement of hardness are fundamental to evaluate some metallic materials properties, like wear resistance, ductility and flow tension. The manual process for hardness measurement is very interpretive and subjective, as the reading of needed values (diameters or diagonals) of the indenter on the material in test depends directly on operator's viewpoint (parallax effect), appropriate calibration of test machine and operator's experience. Additionally, one must notice that operator's fatigue or tiredness, due to a high number of tests done, is highly prone to measurement errors. \newline In this context, the main goals of More >

Abdurazzag Ali Aburas¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.9, No.1, pp. 1-2, 2009, DOI:10.3970/icces.2009.009.001

Abstract The typical Optical Character Recognition (OCR) systems, regardless the character's nature, are based mainly on three stages, preprocessing, features extraction and discrimination (recognizer). Each stage has its own problems and effects on the system efficiency such as time consuming and recognition errors. In order to avoid these difficulties this talk presents new construction of OCR system without pre-processing, features extraction and classifier for any handwriting characters using standard and advanced Image Compression techniques. The proposed algorithms obtained promising results in terms of accuracy as well as in terms of time consuming. More >

Patrícia C.T. Gonçalves^1,2, João Manuel R.S. Tavares¹, R.M. Natal Jorge¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.9, No.3, pp. 203-204, 2009, DOI:10.3970/icces.2009.009.203

Abstract The main goals of the present work are to automatically extract the contour of an object and to simulate its deformation using a physical approach. In this work, to segment an object represented in an image, an initial contour is manually defined for it that will then automatically evolve until it reaches the border of the desired object. In this approach, the contour is modelled by a physical formulation using the finite element method, and its temporal evolution to the desired final contour is driven by internal and external forces. The internal forces are defined… More >

Raquel R. Pinho¹, João Manuel R. S. Tavares¹

CMES-Computer Modeling in Engineering & Sciences, Vol.46, No.1, pp. 51-76, 2009, DOI:10.3970/cmes.2009.046.051

Abstract This work addresses the problem of tracking feature points along image sequences. In order to analyze the undergoing movement, an approach based on the Kalman filtering technique has been used, which basically carries out the estimation and correction of the features' movement in every image frame. So as to integrate the measurements obtained from each image into the Kalman filter, a data optimization process has been adopted to achieve the best global correspondence set. The proposed criterion minimizes the cost of global matching, which is based on the Mahalanobis distance. A management model is employed More >

Francisco P. M. Oliveira¹, João Manuel R. S. Tavares¹

CMES-Computer Modeling in Engineering & Sciences, Vol.43, No.1, pp. 91-110, 2009, DOI:10.3970/cmes.2009.043.091

Abstract This paper presents a new methodology to establish the best global match of objects' contours in images. The first step is the extraction of the sets of ordered points that define the objects' contours. Then, by using the curvature value and its distance to the corresponded centroid for each point, an affinity matrix is built. This matrix contains information of the cost for all possible matches between the two sets of ordered points. Then, to determine the desired one-to-one global matching, an assignment algorithm based on dynamic programming is used. This algorithm establishes the global More >