Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

Evaluation of free libraries for visual recognition of art imagery on mobile devices

This paper describes a systematic research about free software solutions and techniques for art imagery computer recognition problem.

Dance movement patterns recognition

"Es tracta d'un projecte dividit en dues parts independents però complementàries, realitzades per autors diferents. Aquest document conté originàriament altre material i/o programari només consultable a la Biblioteca de Ciència i Tecnologia"

Bioinformàtica: add-in d'anàlisi i manipulació de seqüències per Microsoft Word

L'objectiu del projecte consisteix en el desenvolupament d'un add-in d'anàlisi i manipulació de seqüències, senzill i de fàcil ús, integrable en l'entorn Microsoft Word per permetre la manipulació de seqüències genètiques directament des de Microsoft Word, estalviant temps, en evitar haver de canviar constantment de programa i format per treballar amb elles; i, també, complicacions a l'usuari final. L'add-in ha estat desenvolupat en Visual Basic + VSTO i ofereix diverses funcionalitats d'edició i anàlisi de seqüències, com ara el complement, la recerca de motius o l'alineament.

A Camera-Projector System for Robot Positioning by Visual Servoing

Positioning a robot with respect to objects by using data provided by a camera is a well known technique called visual servoing. In order to perform a task, the object must exhibit visual features which can be extracted from different points of view. Then, visual servoing is object-dependent as it depends on the object appearance. Therefore, performing the positioning task is not possible in presence of nontextured objets or objets for which extracting visual features is too complex or too costly. This paper proposes a solution to tackle this limitation inherent to the current visual servoing techniques. Our proposal is based on the coded structured light approach as a reliable and fast way to solve the correspondence problem. In this case, a coded light pattern is projected providing robust visual features independently of the object appearance

Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition

Several features that can be extracted from digital images of the sky and that can be useful for cloud-type classification of such images are presented. Some features are statistical measurements of image texture, some are based on the Fourier transform of the image and, finally, others are computed from the image where cloudy pixels are distinguished from clear-sky pixels. The use of the most suitable features in an automatic classification algorithm is also shown and discussed. Both the features and the classifier are developed over images taken by two different camera devices, namely, a total sky imager (TSI) and a whole sky imager (WSC), which are placed in two different areas of the world (Toowoomba, Australia; and Girona, Spain, respectively). The performance of the classifier is assessed by comparing its image classification with an a priori classification carried out by visual inspection of more than 200 images from each camera. The index of agreement is 76% when five different sky conditions are considered: clear, low cumuliform clouds, stratiform clouds (overcast), cirriform clouds, and mottled clouds (altocumulus, cirrocumulus). Discussion on the future directions of this research is also presented, regarding both the use of other features and the use of other classification techniques

Memoria de la elaboración de subtítulos para "Babel", primer capítulo de la serie documental Fry's Planet Word

This work tries to identify some of the skills an audio visual translator must develop, from a practical point of view, in order to pursue a career in this field, putting the stress on mastering subtitling-specific software. This report describes trial and error process during the making of the subtitles for a documentary and identifies some of the difficulties we might encounter while working on an assignment of this kind if we work with free licensing software. Moreover, it tries to contribute with some answers to these issues.

Semantic domain and grammatical class effects in the picture-word interference paradigm

The role of grammatical class in lexical access and representation is still not well understood. Grammatical effects obtained in picture-word interference experiments have been argued to show the operation of grammatical constraints during lexicalization when syntactic integration is required by the task. Alternative views hold that the ostensibly grammatical effects actually derive from the coincidence of semantic and grammatical differences between lexical candidates. We present three picture-word interference experiments conducted in Spanish. In the first two, the semantic relatedness (related or unrelated) and the grammatical class (nouns or verbs) of the target and the distracter were manipulated in an infinitive form action naming task in order to disentangle their contributions to verb lexical access. In the third experiment, a possible confound between grammatical class and semantic domain (objects or actions) was eliminated by using action-nouns as distracters. A condition in which participants were asked to name the action pictures using an inflected form of the verb was also included to explore whether the need of syntactic integration modulated the appearance of grammatical effects. Whereas action-words (nouns or verbs), but not object-nouns, produced longer reaction times irrespective of their grammatical class in the infinitive condition, only verbs slowed latencies in the inflected form condition. Our results suggest that speech production relies on the exclusion of candidate responses that do not fulfil task-pertinent criteria like membership in the appropriate semantic domain or grammatical class. Taken together, these findings are explained by a response-exclusion account of speech output. This and alternative hypotheses are discussed.

Memoria de la elaboración de subtítulos para "Babel", primer capítulo de la serie documental Fry's Planet Word

Este trabajo pretende identificar algunas de las habilidades que un traductor audiovisual debe desarrollar, desde un punto de vista práctico, para ejercer la profesión, haciendo hincapié en el dominio del software específico para subtituladores. Esta memoria describe el proceso de ensayo y error llevado a cabo durante la elaboración de los subtítulos de un documental e identifica algunas de las dificultades con las que podemos encontrarnos al realizar un encargo de este tipo si trabajamos con programas de licencia gratuita, además de intentar aportar las soluciones correspondientes.

Implementació amb Visual Basic d'un algorisme per a encriptar i desencriptar

Treball de recerca realitzat per un alumne d’ensenyament secundari i guardonat amb un Premi CIRIT per fomentar l'esperit científic del Jovent l’any 2005. La criptografia és l’art d’escriure un llenguatge convingut, amb l’ús d’unes claus i de la seva operació inversa se’n diu criptoanalitzar. Els sistemes criptogràfics han estat emprats al llarg de la història. Actualment existeixen multituds de software i de hardware destinats a analitzar el tràfic de dades en xarxes de computadores. Encara que aquestes eines constitueixen un avenç en tècniques de seguretat i protecció, el seu ús indegut es al mateix temps un greu problema i una enorme font d’atacs a la intimitat dels seus usuaris i a la integritat dels seus propis sistemes. Des d’aquest punt de vista, s’explica com s’ha dissenyat dos aplicacions informàtiques per encriptar i desencriptar.

The word problem distinguishes counter languages

Counter automata are more powerful versions of finite state automata where addition and subtraction operations are permitted on a set of n integer registers, called counters. We show that the word problem of Zn is accepted by a nondeterministic m-counter automaton if and only if m &= n.

Generador de ofertas

Actualmente en TELSTAR SA el sistema de generación de ofertas se realiza de distintas formas dependiendo de la empresa que se trate. Una manera es a través de formularios creados en documentos Word, programados con macros escritas en Visual Basic. Otro modo es creando documentos a partir de ofertas similares, modificando su contenido de forma manual. Ante esta situación se hace necesario una mejora en el sistema de generación de ofertas de tal forma que este proceso sea más eficiente y –lo más importante- se eviten errores. Además, el sistema propuesto debe ser fácil de utilizar por las distintas partes implicadas en la confección de las propuestas de venta.

Object recognition for autonomous objects: comparison of two approaches

Report for the scientific sojourn at the Swiss Federal Institute of Technology Zurich, Switzerland, between September and December 2007. In order to make robots useful assistants for our everyday life, the ability to learn and recognize objects is of essential importance. However, object recognition in real scenes is one of the most challenging problems in computer vision, as it is necessary to deal with difficulties. Furthermore, in mobile robotics a new challenge is added to the list: computational complexity. In a dynamic world, information about the objects in the scene can become obsolete before it is ready to be used if the detection algorithm is not fast enough. Two recent object recognition techniques have achieved notable results: the constellation approach proposed by Lowe and the bag of words approach proposed by Nistér and Stewénius. The Lowe constellation approach is the one currently being used in the robot localization project of the COGNIRON project. This report is divided in two main sections. The first section is devoted to briefly review the currently used object recognition system, the Lowe approach, and bring to light the drawbacks found for object recognition in the context of indoor mobile robot navigation. Additionally the proposed improvements for the algorithm are described. In the second section the alternative bag of words method is reviewed, as well as several experiments conducted to evaluate its performance with our own object databases. Furthermore, some modifications to the original algorithm to make it suitable for object detection in unsegmented images are proposed.

Impacte visual aeri a Argentona

Treball de recerca realitzat per un alumne d'ensenyament secundari i guardonat amb un Premi CIRIT per fomentar l'esperit cientí­fic del Jovent l'any 2009. Aquest treball té com a finalitat millorar l'entorn aeri d'Argentona, un poble situat a la comarca del Maresme. Els elements que creen més impacte visual aeri són les antenes en desús i el cablejat no soterrat. S'han buscat propostes per canviar aquesta situació: la retirada de les antenes, aprofitant l'arribada de la TDT, i el soterrament del cablejat aeri. Donat que ambdues accions afectarien al municipi i a la seva població, s'ha considerat necessari incloure una enquesta, per a conèixer l'opinió dels argentonins, i dues entrevistes, a l'alcalde i a l'enginyer municipal, per conèixer la postura oficial.

Effects of Bilingualism on Multi-Word Production

It has been shown that bilinguals are disadvantaged on some language production tasks when compared to monolinguals. The present study investigated the effects of bilingualism on lexical retrieval in single and multi-word utterances. To this purpose, we tested three groups of 35 participants each (Spanish monolinguals, highly proficient Spanish-Catalan and Catalan-Spanish bilinguals) in two sets of picture naming experiments. In the first one, participants were asked to name black-and-white object drawings by single words. In the second one, participants had to name colored pictures with determiner adjectival noun phrases (NP) like “the red car”. In both sets of experiments, bilinguals were slower than monolinguals, even when naming in their dominant language. We also examined the articulatory durations of both single word and NP productions for this bilingual disadvantage. Furthermore, response onset times and durations of all groups in both experiments were affected by lexical variables of the picture names. These results are consistent with previous studies (Ivanova & Costa, 2008, Gollan et al., 2005) showing a bilingual disadvantage in single word production and extend these findings to multiword-utterances and response durations. They also support the claim that articulatory processes are influenced by lexical variables.