Component based recognition of objects in an office environment

We present a component-based approach for recognizing objects under large pose changes. From a set of training images of a given object we extract a large number of components which are clustered based on the similarity of their image features and their locations within the object image. The cluster centers build an initial set of component templates from which we select a subset for the final recognizer. In experiments we evaluate different sizes and types of components and three standard techniques for component selection. The component classifiers are finally compared to global classifiers on a database of four objects.

On the difficulty of feature-based attentional modulations in visual object recognition: A modeling study.

Numerous psychophysical experiments have shown an important role for attentional modulations in vision. Behaviorally, allocation of attention can improve performance in object detection and recognition tasks. At the neural level, attention increases firing rates of neurons in visual cortex whose preferred stimulus is currently attended to. However, it is not yet known how these two phenomena are linked, i.e., how the visual system could be "tuned" in a task-dependent fashion to improve task performance. To answer this question, we performed simulations with the HMAX model of object recognition in cortex [45]. We modulated firing rates of model neurons in accordance with experimental results about effects of feature-based attention on single neurons and measured changes in the model's performance in a variety of object recognition tasks. It turned out that recognition performance could only be improved under very limited circumstances and that attentional influences on the process of object recognition per se tend to display a lack of specificity or raise false alarm rates. These observations lead us to postulate a new role for the observed attention-related neural response modulations.

Rotation Invariant Object Recognition from One Training Example

Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Such a descriptor--based on a set of oriented Gaussian derivative filters-- is used in our recognition system. We report here an evaluation of several techniques for orientation estimation to achieve rotation invariance of the descriptor. We also describe feature selection based on a single training image. Virtual images are generated by rotating and rescaling the image and robust features are selected. The results confirm robust performance in cluttered scenes, in the presence of partial occlusions, and when the object is embedded in different backgrounds.

Uncertainty Propagation in Model-Based Recognition

Building robust recognition systems requires a careful understanding of the effects of error in sensed features. Error in these image features results in a region of uncertainty in the possible image location of each additional model feature. We present an accurate, analytic approximation for this uncertainty region when model poses are based on matching three image and model points, for both Gaussian and bounded error in the detection of image points, and for both scaled-orthographic and perspective projection models. This result applies to objects that are fully three- dimensional, where past results considered only two-dimensional objects. Further, we introduce a linear programming algorithm to compute the uncertainty region when poses are based on any number of initial matches. Finally, we use these results to extend, from two-dimensional to three- dimensional objects, robust implementations of alignmentt interpretation- tree search, and ransformation clustering.

Geometric Aspects of Visual Object Recognition

This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.

Learning Three-Dimensional Shape Models for Sketch Recognition

Artifacts made by humans, such as items of furniture and houses, exhibit an enormous amount of variability in shape. In this paper, we concentrate on models of the shapes of objects that are made up of fixed collections of sub-parts whose dimensions and spatial arrangement exhibit variation. Our goals are: to learn these models from data and to use them for recognition. Our emphasis is on learning and recognition from three-dimensional data, to test the basic shape-modeling methodology. In this paper we also demonstrate how to use models learned in three dimensions for recognition of two-dimensional sketches of objects.

ROC parameters in item and context recognition. 'Par??metros ROC en el reconocimiento de items y contextos'

Resumen tomado de la publicaci??n. Resumen tambi??n en ingl??s

Use of decision trees in colour feature selection: application to object recognition in outdoor scenes

A new method for the automated selection of colour features is described. The algorithm consists of two stages of processing. In the first, a complete set of colour features is calculated for every object of interest in an image. In the second stage, each object is mapped into several n-dimensional feature spaces in order to select the feature set with the smallest variables able to discriminate the remaining objects. The evaluation of the discrimination power for each concrete subset of features is performed by means of decision trees composed of linear discrimination functions. This method can provide valuable help in outdoor scene analysis where no colour space has been demonstrated as being the most suitable. Experiment results recognizing objects in outdoor scenes are reported

Model-based objects recognition in industrial environments for autonomous vehicles control

Behavior-based navigation of autonomous vehicles requires the recognition of the navigable areas and the potential obstacles. In this paper we describe a model-based objects recognition system which is part of an image interpretation system intended to assist the navigation of autonomous vehicles that operate in industrial environments. The recognition system integrates color, shape and texture information together with the location of the vanishing point. The recognition process starts from some prior scene knowledge, that is, a generic model of the expected scene and the potential objects. The recognition system constitutes an approach where different low-level vision techniques extract a multitude of image descriptors which are then analyzed using a rule-based reasoning system to interpret the image content. This system has been implemented using a rule-based cooperative expert system

Model-based objects recognition in man-made environments

We describe a model-based objects recognition system which is part of an image interpretation system intended to assist autonomous vehicles navigation. The system is intended to operate in man-made environments. Behavior-based navigation of autonomous vehicles involves the recognition of navigable areas and the potential obstacles. The recognition system integrates color, shape and texture information together with the location of the vanishing point. The recognition process starts from some prior scene knowledge, that is, a generic model of the expected scene and the potential objects. The recognition system constitutes an approach where different low-level vision techniques extract a multitude of image descriptors which are then analyzed using a rule-based reasoning system to interpret the image content. This system has been implemented using CEES, the C++ embedded expert system shell developed in the Systems Engineering and Automatic Control Laboratory (University of Girona) as a specific rule-based problem solving tool. It has been especially conceived for supporting cooperative expert systems, and uses the object oriented programming paradigm

A new approach to real time traffic sign recognition based on colour information

The automatic interpretation of conventional traffic signs is very complex and time consuming. The paper concerns an automatic warning system for driving assistance. It does not interpret the standard traffic signs on the roadside; the proposal is to incorporate into the existing signs another type of traffic sign whose information will be more easily interpreted by a processor. The type of information to be added is profuse and therefore the most important object is the robustness of the system. The basic proposal of this new philosophy is that the co-pilot system for automatic warning and driving assistance can interpret with greater ease the information contained in the new sign, whilst the human driver only has to interpret the "classic" sign. One of the codings that has been tested with good results and which seems to us easy to implement is that which has a rectangular shape and 4 vertical bars of different colours. The size of these signs is equivalent to the size of the conventional signs (approximately 0.4 m2). The colour information from the sign can be easily interpreted by the proposed processor and the interpretation is much easier and quicker than the information shown by the pictographs of the classic signs

Iniciativas de mujeres gestoras de paz en Colombia

La búsqueda de alternativas que frenen eficazmente las consecuencias del conflicto armado en Colombia, es una labor que algunos ex mandatarios han liderado debido a los perjuicios que ocasionan no solo al núcleo familiar, sino en gran medida a la mujer. Ella es una de las víctimas de la violencia por ser líder comunitaria, por dirigir una fundación, ó por tener algún familiar vinculado a la Policía, el Ejército o a un grupo al margen de la ley. Todas estas condiciones, propias del conflicto armado, vulneran los derechos de la mujer pero, al mismo tiempo, impulsa a que ellas hagan uso de sus experiencias negativas con el fin de minimizar las problemáticas sociales y el impacto de la violencia en sus vidas. Este trabajo periodístico desarrolla cuatro reportajes mediante el uso de cuestionarios con preguntas a profundidad y es complementado con un video, con el propósito de destacar la lucha y la labor de cuatro gestoras de paz, quienes utilizan diferentes estrategias como la creación de movimientos sociales, la utilización de marchas o plantones, la divulgación de talleres sobre el perdón y reconciliación, o la construcción de un Banco del Trueque, para contrarrestar la violencia de la que son objeto. Se concluye que el papel de la mujer, como constructora de paz, no puede ser clasificado en un único objetivo, sino debe entenderse como la suma de múltiples prioridades debido a que el conflicto armado afecta de diferente manera a la mujer, a su familia, y a su comunidad. Su capacidad de liderazgo y de entrega hace que su labor sea de suma importancia pues su huella beneficia a toda la sociedad. Hay que destacar que el desafío de esta nueva gestora consiste en visibilizar su trabajo para ganar mayor reconocimiento político, promover su participación en acuerdos de paz, y minimizar las situaciones que ponen en riesgo su vida y la de sus organizaciones.

PLAN-DO-CHECK-ACT en una experiencia TIC en el aula : desde la idea a la evaluación.

Resumen tomado del autor

Professional Recognition of Educator Practice Framework Handbook

UoS CPD Framework route

Descripción de la estructura organizacional del área de Responsabilidad Social del Helm Bank en el año 2012

La investigación que se presenta a continuación reconstruye las acciones de la Responsabilidad Social Empresarial en el sector financiero Colombiano, congregando información académica donde los autores; teóricos y ejecutores, analizan y ofrecen pautas para el actuar responsable y sostenible en una organización. Así mismo este trabajo pone a la vista del lector información recopilada fruto de fuentes primarias, producto de conversaciones con la directiva en el área de Sostenibilidad del Helm Bank, integrante del sector financiero Colombiano y al gremio de bancos más relevantes en el país ASOBANCARIA. El direccionamiento de esta investigación se centra en la identificación del diseño estructural de un área de RSE en el sector financiero y sus componentes definidos en las siguientes variables; Evolución del área, Coordinación del trabajo, División laboral y Plataforma Estratégica Como resultado de dicha investigación se encontraron interesantes elementos. Dentro de estos elementos se hace especial mención a la sinergia que unen la planeación estratégica empresarial con las prácticas de Sostenibilidad, la directa conexión de la alta gerencia con el área de Responsabilidad Empresarial y con especial agrado la enorme puesta en marcha de acciones responsables en las tres dimensiones; social, ambiental y económica por parte de algunas entidades de la banca nacional en torno a sus actores de interés.