Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images

In model-based vision, there are a huge number of possible ways to match model features to image features. In addition to model shape constraints, there are important match-independent constraints that can efficiently reduce the search without the combinatorics of matching. I demonstrate two specific modules in the context of a complete recognition system, Reggie. The first is a region-based grouping mechanism to find groups of image features that are likely to come from a single object. The second is an interpretive matching scheme to make explicit hypotheses about occlusion and instabilities in the image features.

Feature Point Detection and Curve Approximation for Early Processing of Freehand Sketches

Freehand sketching is both a natural and crucial part of design, yet is unsupported by current design automation software. We are working to combine the flexibility and ease of use of paper and pencil with the processing power of a computer to produce a design environment that feels as natural as paper, yet is considerably smarter. One of the most basic steps in accomplishing this is converting the original digitized pen strokes in the sketch into the intended geometric objects using feature point detection and approximation. We demonstrate how multiple sources of information can be combined for feature detection in strokes and apply this technique using two approaches to signal processing, one using simple average based thresholding and a second using scale space.

Extensión de la especificación IMS Learning Design desde la adaptación e integración de unidades de aprendizaje. `Extension of the IMS Learnin Design specification based on adaptation and integration of units of learning´.

La tesis se centra en el aprendizaje personalizado y en la integración de Unidades de Aprendizaje. El objetivo fundamental es mejorar la expresividad pedagógica de IMS-LD, refinando estructuras de modelado y arquitectura existentes y desarrollando estructuras complementarias que permitan una formalización más precisa, versátil y sencilla de procesos de aprendizaje adaptativo y de mecanismos y procesos de integración con sistemas de aprendizaje y otras especificaciones. En esta tesis se estudia la especificación desde la base, analizando su modelo de información y cómo se construyen Unidades de Aprendizaje. Se analiza la estructura de la especificación, basándose en un estudio teórico y una investigación práctica fruto del modelado de Unidades de Aprendizaje reales y ejecutables que proporcionan una información útil de base. A partir de este estudio, se analiza la integración de Unidades de Aprendizaje con otros sistemas y especificaciones, abarcando desde la integración mínima mediante un enlace directo hasta compartir variables y estados que permiten una comunicación en tiempo real de ambas partes. La conclusión es que IMS-LD necesita una reestructuración y modificación de ciertos elementos, así como la incorporación de otros nuevos, para mejorar una expresividad pedagógica y una capacidad de integración con otros sistemas de aprendizaje y estándares eLearning, si se pretenden alcanzar: la personalización del proceso de aprendizaje y la interoperabilidad real. La implantación de la especificación se vería mejorada si existieran unas herramientas de más alto nivel, preferiblemente con planteamiento visual, que permitieran un modelado sencillo por parte de los usuarios finales reales de este tipo de especificaciones, como son los profesores, los creadores de contenido y los pedagogos-didactas que diseñan la experiencia de aprendizaje.

Catadioptric stereo based on structured light projection

La percepció per visió es millorada quan es pot gaudir d'un camp de visió ampli. Aquesta tesi es concentra en la percepció visual de la profunditat amb l'ajuda de càmeres omnidireccionals. La percepció 3D s'obté generalment en la visió per computadora utilitzant configuracions estèreo amb el desavantatge del cost computacional elevat a l'hora de buscar els elements visuals comuns entre les imatges. La solució que ofereix aquesta tesi és l'ús de la llum estructurada per resoldre el problema de relacionar les correspondències. S'ha realitzat un estudi sobre els sistemes de visió omnidireccional. S'han avaluat vàries configuracions estèreo i s'ha escollit la millor. Els paràmetres del model són difícils de mesurar directament i, en conseqüència, s'ha desenvolupat una sèrie de mètodes de calibració. Els resultats obtinguts són prometedors i demostren que el sensor pot ésser utilitzat en aplicacions per a la percepció de la profunditat com serien el modelatge de l'escena, la inspecció de canonades, navegació de robots, etc.

Design and optimisation of a large-area process-based model for annual crops

The formulation of a new process-based crop model, the general large-area model (GLAM) for annual crops is presented. The model has been designed to operate on spatial scales commensurate with those of global and regional climate models. It aims to simulate the impact of climate on crop yield. Procedures for model parameter determination and optimisation are described, and demonstrated for the prediction of groundnut (i.e. peanut; Arachis hypogaea L.) yields across India for the period 1966-1989. Optimal parameters (e.g. extinction coefficient, transpiration efficiency, rate of change of harvest index) were stable over space and time, provided the estimate of the yield technology trend was based on the full 24-year period. The model has two location-specific parameters, the planting date, and the yield gap parameter. The latter varies spatially and is determined by calibration. The optimal value varies slightly when different input data are used. The model was tested using a historical data set on a 2.5degrees x 2.5degrees grid to simulate yields. Three sites are examined in detail-grid cells from Gujarat in the west, Andhra Pradesh towards the south, and Uttar Pradesh in the north. Agreement between observed and modelled yield was variable, with correlation coefficients of 0.74, 0.42 and 0, respectively. Skill was highest where the climate signal was greatest, and correlations were comparable to or greater than correlations with seasonal mean rainfall. Yields from all 35 cells were aggregated to simulate all-India yield. The correlation coefficient between observed and simulated yields was 0.76, and the root mean square error was 8.4% of the mean yield. The model can be easily extended to any annual crop for the investigation of the impacts of climate variability (or change) on crop yield over large areas. (C) 2004 Elsevier B.V. All rights reserved.

Design of mucoadhesive polymeric films based on blends of poly(acrylic acid) and (hydroxypropyl)cellulose

Mixing of aqueous solutions of poly(acrylic acid) and (hydroxypropyl) cellulose results in formation of hydrogen-bonded interpolymer complexes, which precipitate and do not allow preparation of homogeneous polymeric films by casting. In the present work the effect of pH on the complexation between poly(acrylic acid) and (hydroxypropyl)cellulose in solutions and miscibility of these polymers in solid state has been studied. The pH-induced complexation-miscibility-immiscibility transitions in the polymer mixtures have been observed. The optimal conditions for preparation of homogeneous polymeric films based on blends of these polymers have been found, and the possibility of radiation cross-linking of these materials has been demonstrated. Although the gamma-radiation treatment of solid polymeric blends was found to be inefficient, successful cross-linking was achieved by addition of N, N'- methylenebis(acrylamide). The mucoadhesive potential of both soluble and cross-linked films toward porcine buccal mucosa is evaluated. Soluble films adhered to mucosal tissues undergo dissolution within 30-110 min depending on the polymer ratio in the blend. Cross-linked films are retained on the mucosal surface for 10-40 min and then detach.

Design and evaluation of intelligent classifier based intrusion detection system

We have discovered a novel approach of intrusion detection system using an intelligent data classifier based on a self organizing map (SOM). We have surveyed all other unsupervised intrusion detection methods, different alternative SOM based techniques and KDD winner IDS methods. This paper provides a robust designed and implemented intelligent data classifier technique based on a single large size (30x30) self organizing map (SOM) having the capability to detect all types of attacks given in the DARPA Archive 1999 the lowest false positive rate being 0.04 % and higher detection rate being 99.73% tested using full KDD data sets and 89.54% comparable detection rate and 0.18% lowest false positive rate tested using corrected data sets.

Sparse kernel density estimator using orthogonal regression based on D-optimality experimental design

A novel sparse kernel density estimator is derived based on a regression approach, which selects a very small subset of significant kernels by means of the D-optimality experimental design criterion using an orthogonal forward selection procedure. The weights of the resulting sparse kernel model are calculated using the multiplicative nonnegative quadratic programming algorithm. The proposed method is computationally attractive, in comparison with many existing kernel density estimation algorithms. Our numerical results also show that the proposed method compares favourably with other existing methods, in terms of both test accuracy and model sparsity, for constructing kernel density estimates.

Design, implementation and testing of an intelligent knowledge-based system for the supervisory control of a hot rolling mill

This paper describes the design, implementation and testing of an intelligent knowledge-based supervisory control (IKBSC) system for a hot rolling mill process. A novel architecture is used to integrate an expert system with an existing supervisory control system and a new optimization methodology for scheduling the soaking pits in which the material is heated prior to rolling. The resulting IKBSC system was applied to an aluminium hot rolling mill process to improve the shape quality of low-gauge plate and to optimise the use of the soaking pits to reduce energy consumption. The results from the trials demonstrate the advantages to be gained from the IKBSC system that integrates knowledge contained within data, plant and human resources with existing model-based systems. (c) 2005 Elsevier Ltd. All rights reserved.

Regression based D-optimality experimental design for sparse kernel density estimation

This paper derives an efficient algorithm for constructing sparse kernel density (SKD) estimates. The algorithm first selects a very small subset of significant kernels using an orthogonal forward regression (OFR) procedure based on the D-optimality experimental design criterion. The weights of the resulting sparse kernel model are then calculated using a modified multiplicative nonnegative quadratic programming algorithm. Unlike most of the SKD estimators, the proposed D-optimality regression approach is an unsupervised construction algorithm and it does not require an empirical desired response for the kernel selection task. The strength of the D-optimality OFR is owing to the fact that the algorithm automatically selects a small subset of the most significant kernels related to the largest eigenvalues of the kernel design matrix, which counts for the most energy of the kernel training data, and this also guarantees the most accurate kernel weight estimate. The proposed method is also computationally attractive, in comparison with many existing SKD construction algorithms. Extensive numerical investigation demonstrates the ability of this regression-based approach to efficiently construct a very sparse kernel density estimate with excellent test accuracy, and our results show that the proposed method compares favourably with other existing sparse methods, in terms of test accuracy, model sparsity and complexity, for constructing kernel density estimates.