Face Recognition using Probabilistic Neural Networks

In this paper we address the problem of face detection and recognition of grey scale frontal view images. We propose a face recognition system based on probabilistic neural networks (PNN) architecture. The system is implemented using voronoi/ delaunay tessellations and template matching. Images are segmented successfully into homogeneous regions by virtue of voronoi diagram properties. Face verification is achieved using matching scores computed by correlating edge gradients of reference images. The advantage of classification using PNN models is its short training time. The correlation based template matching guarantees good classification results

Face Recognition using Probabilistic Neural Networks

n this paper we address the problem of face detection and recognition of grey scale frontal view images. We propose a face recognition system based on probabilistic neural networks (PNN) architecture. The system is implemented using voronoi/ delaunay tessellations and template matching. Images are segmented successfully into homogeneous regions by virtue of voronoi diagram properties. Face verification is achieved using matching scores computed by correlating edge gradients of reference images. The advantage of classification using PNN models is its short training time. The correlation based template matching guarantees good classification results.

Strategienentwicklung zur Aufwertung von Restflächen am Beispiel ausgewählter Flächen im Stadtteil Nord-Holland in Kassel

Eine kleine Grünfläche im städtischen Freiraum, eine Baumscheibe, ca. 5 m² groß, öffentlich zugänglich. Dort wo eigentlich blühende Pflanzen das Straßenbild verschönern könnten, sieht man alle zwei Wochen, wenn es wieder auf den Müllabholungstag zugeht, eine Lawine aus Gelben Säcken, die immer weiter über die Grünfläche zu rollen scheint, und so auch das letzte bisschen Grün unter sich begräbt. Und die Gelben Lawinen beschränken sich dabei nicht nur auf eine einzelne Fläche, sondern nehmen gleich ganze Straßenzüge in Beschlag. Diese Beobachtungen im Kassler Stadtteil Nord-Holland bildeten den ersten Impuls für das Thema der vorliegenden Arbeit. Es entstand die Überlegung, ob diese gravierende Vermüllung der Flächen und damit die Abwertung des gesamten Straßenbildes (wenn nicht sogar des gesamten Stadtteils) nur eine persönliche Wahrnehmung ist oder ob es durchaus andere Menschen (und besonders die direkten Anwohner) gibt, die diese Ansicht teilen. Auch kam die Frage auf, wie hoch die Wertschätzung der Flächen von Seiten der Kommune her einzuschätzen ist. Unter Berücksichtigung der scheinbar zunehmend knapper werdenden Haushaltsmittel der Kommune, für die Pflege öffentlicher Grünflächen, in Kombination mit dem sich immer weiter verbreitenden Trend des „Urbanen Gärtnerns“, entstand die Idee, Strategien zur Aufwertung der Flächen zu entwickeln, dessen Grundlage aus einer Kooperation zwischen der Kommune und privaten Akteuren besteht. Wer diese Akteure sind (bzw. seien könnten), welche Bedürfnisse sie haben, wie sie zu einem Engagement ihrerseits motiviert werden und wie konkrete Projekte zur Aufwertung der Flächen aussehen können, soll in dieser Masterarbeit vorgestellt werden. Da der Stadtteil Nord-Holland im allgemeinen als „Sozialer Brennpunkt“ gilt (besonders der nördliche Teil), ist zu erwarten, dass besonders die Initiierung des Engagements der privaten Akteure dabei eine zusätzliche Herausforderung darstellen wird. Da es bereits verschiedene Strategien zur Aufwertung von städtischen Grünflächen gibt, sollen einige von ihnen, sowohl aus Kassel als auch aus anderen Städten, betrachtet und auf ihre Anwendbarkeit auf die ausgewählten Flächen geprüft werden.

Rotation Invariant Real-time Face Detection and Recognition System

In this report, a face recognition system that is capable of detecting and recognizing frontal and rotated faces was developed. Two face recognition methods focusing on the aspect of pose invariance are presented and evaluated - the whole face approach and the component-based approach. The main challenge of this project is to develop a system that is able to identify faces under different viewing angles in realtime. The development of such a system will enhance the capability and robustness of current face recognition technology. The whole-face approach recognizes faces by classifying a single feature vector consisting of the gray values of the whole face image. The component-based approach first locates the facial components and extracts them. These components are normalized and combined into a single feature vector for classification. The Support Vector Machine (SVM) is used as the classifier for both approaches. Extensive tests with respect to the robustness against pose changes are performed on a database that includes faces rotated up to about 40 degrees in depth. The component-based approach clearly outperforms the whole-face approach on all tests. Although this approach isproven to be more reliable, it is still too slow for real-time applications. That is the reason why a real-time face recognition system using the whole-face approach is implemented to recognize people in color video sequences.

Example Based Learning for View-Based Human Face Detection

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image location, the local pattern is matched against the distribution-based model, and a trained classifier determines, based on the local difference measurements, whether or not a human face exists at the current image location. We provide an analysis that helps identify the critical components of our system.

Conditions for Viewpoint Dependent Face Recognition

Poggio and Vetter (1992) showed that learning one view of a bilaterally symmetric object could be sufficient for its recognition, if this view allows the computation of a symmetric, "virtual," view. Faces are roughly bilaterally symmetric objects. Learning a side-view--which always has a symmetric view--should allow for better generalization performances than learning the frontal view. Two psychophysical experiments tested these predictions. Stimuli were views of shaded 3D models of laser-scanned faces. The first experiment tested whether a particular view of a face was canonical. The second experiment tested which single views of a face give rise to best generalization performances. The results were compatible with the symmetry hypothesis: Learning a side view allowed better generalization performances than learning the frontal view.

Face Detection in Still Gray Images

We present a trainable system for detecting frontal and near-frontal views of faces in still gray images using Support Vector Machines (SVMs). We first consider the problem of detecting the whole face pattern by a single SVM classifer. In this context we compare different types of image features, present and evaluate a new method for reducing the number of features and discuss practical issues concerning the parameterization of SVMs and the selection of training data. The second part of the paper describes a component-based method for face detection consisting of a two-level hierarchy of SVM classifers. On the first level, component classifers independently detect components of a face, such as the eyes, the nose, and the mouth. On the second level, a single classifer checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face.

Support Vector Machines: Training and Applications

The Support Vector Machine (SVM) is a new and very promising classification technique developed by Vapnik and his group at AT&T Bell Labs. This new learning algorithm can be seen as an alternative training technique for Polynomial, Radial Basis Function and Multi-Layer Perceptron classifiers. An interesting property of this approach is that it is an approximate implementation of the Structural Risk Minimization (SRM) induction principle. The derivation of Support Vector Machines, its relationship with SRM, and its geometrical insight, are discussed in this paper. Training a SVM is equivalent to solve a quadratic programming problem with linear and box constraints in a number of variables equal to the number of data points. When the number of data points exceeds few thousands the problem is very challenging, because the quadratic form is completely dense, so the memory needed to store the problem grows with the square of the number of data points. Therefore, training problems arising in some real applications with large data sets are impossible to load into memory, and cannot be solved using standard non-linear constrained optimization algorithms. We present a decomposition algorithm that can be used to train SVM's over large data sets. The main idea behind the decomposition is the iterative solution of sub-problems and the evaluation of, and also establish the stopping criteria for the algorithm. We present previous approaches, as well as results and important details of our implementation of the algorithm using a second-order variant of the Reduced Gradient Method as the solver of the sub-problems. As an application of SVM's, we present preliminary results we obtained applying SVM to the problem of detecting frontal human faces in real images.

Object Detection in Images by Components

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

Impact of the proliferation of information and technology in Higher Education

Resumen tomado de la publicaci??n

Disseny i implementació d'un dispositiu de localització GPS

L'objectiu final d'aquest projecte ha estat el de fer un localitzador GPS. Inicialment es parteix d'un mòdul LCD amb retroil•luminació Optrex DMF-5005N i un mòdul GPS Connexant TU30. De la unió d'aquests dos, més la circuiteria dissenyada, en sorgeix un sistema capaç de proporcionar dades fiables i útils per a l'usuari, com són les coordenades, la velocitat, l'alçada, la data i l'hora, entre d'altres. El resultat final del projecte està contingut en una carcassa al frontal de la qual, hi podem veure el panell LCD, un pulsador per canvi de pantalla i un altre per variar la velocitat de quilòmetres per hora a nusos i a la inversa

Funciones ejecutivas y rendimiento escolar en educaci??n primaria : un estudio exploratorio

Resumen de los autores. Res??menes en espa??ol e ingl??s

Los Comandos Conjuntos en el desempeño de las Fuerzas Militares de Colombia en la lucha contrainsurgente. Caso específico: Comando Conjunto Número 1 Caribe

Esta monografía busca examinar el papel del Comando Conjunto en Colombia en el desempeño de las Fuerzas Militares en la lucha contrainsurgente. Se tomará como caso específico de estudio el Comando Conjunto “Número 1 Caribe”, partiendo desde las metas y responsabilidades impuestas a las Fuerzas por la Política de Seguridad Democrática en el año 2003 en cuanto a la lucha frontal contra los grupos guerrilleros, de autodefensas, de delincuencia común y de narcotráfico, haciendo énfasis en la consolidación territorial, el mantenimiento de la capacidad disuasiva y el fortalecimiento de ellas mismas.

Estimation of zero-sequence impedance of undergrounds cables for single-phase fault location in distribution systems with electric arc

This paper focus on the problem of locating single-phase faults in mixed distribution electric systems, with overhead lines and underground cables, using voltage and current measurements at the sending-end and sequence model of the network. Since calculating series impedance for underground cables is not as simple as in the case of overhead lines, the paper proposes a methodology to obtain an estimation of zero-sequence impedance of underground cables starting from previous single-faults occurred in the system, in which an electric arc occurred at the fault location. For this reason, the signal is previously pretreated to eliminate its peaks voltage and the analysis can be done working with a signal as close as a sinus wave as possible

Anatomia de la auriculilla izquierda: análisis comparativo por ecocardiografia transesofagica bidimensional y tridimensional

Introducción. La auriculilla izquierda es una estructura cardiaca que facilita la generación de trombos en su interior, favoreciendo la aparición de evento embolicos, por lo que su análisis a partir de imágenes bidimensionales y mas recientemente tridimensionales, adquieren cada vez mayor importancia Objetivo. Comparar los hallazgos anatómicos de la auriculilla izquierda obtenidos a través de la ecocardiografía tridimensional con respecto a los obtenidos por ecocardiografía bidimensional en un grupo de pacientes con ritmo sinusal y con fibrilación auricular. Métodos. Se trata de un estudio observacional analítico, transversal, en el que se compararan los resultados en las mediciones anatómicas obtenidas por ecocardiograma bidimensional en pacientes con rimo sinusal y fibrilación auricular, con los resultados de dichas mediciones obtenidas a través del ecocardiograma tridimensional en el mismo grupo de pacientes. Resultados. Se evaluaron 48 pacientes, 32 pacientes (66%) se encontraron en ritmo sinusal, la edad promedio fue de 58,2 años; 41,7% fueron mujeres y la mayoría, 32 pacientes (66,7%), tenían una o varias comorbilidades de importancia de riesgo cardiovascular, con evidencia de compromiso de la función sistólica en 20 paciente, encontrando una mayor homogeneidad en las variables área y profundidad de la auriculilla izquierda. Discusión. Los resultados nos permiten apoyar el concepto que las imágenes obtenidas por ecocardiografía tridimensional nos ofrecen una mejor evaluación de la auriculilla izquierda, observando una mayor homogeneidad con la ecocardiografía bidimensional en las variables área y profundidad, existiendo a su vez heterogeneidad en la variable longitud. Conclusión. El presente estudio demostró que la ecocardiografía tridimensional, es un aporte importante desde el punto de vista diagnostico tanto cualitativo como cuantitativo en el análisis de la auriculilla izquierda, permitiendo una fácil adquisición de imágenes en tiempo real y comparativas con las imágenes bidimensionales.