Chaotic phase synchronization and desynchronization in an oscillator network for object selection

Object selection refers to the mechanism of extracting objects of interest while ignoring other objects and background in a given visual scene. It is a fundamental issue for many computer vision and image analysis techniques and it is still a challenging task to artificial Visual systems. Chaotic phase synchronization takes place in cases involving almost identical dynamical systems and it means that the phase difference between the systems is kept bounded over the time, while their amplitudes remain chaotic and may be uncorrelated. Instead of complete synchronization, phase synchronization is believed to be a mechanism for neural integration in brain. In this paper, an object selection model is proposed. Oscillators in the network representing the salient object in a given scene are phase synchronized, while no phase synchronization occurs for background objects. In this way, the salient object can be extracted. In this model, a shift mechanism is also introduced to change attention from one object to another. Computer simulations show that the model produces some results similar to those observed in natural vision systems.

La risa en los Chistes de Facebook

People tell jokes in order to amuse and produce laughter. It is possible to represent laughter in the cyberspace discourse by writing how it sounds or by using a representation of a facial expression formed by various combinations of keyboard characters called emoticon. Jokes are appreciated by both men and women in our society but is there any difference between the way they represent laughter in the cyberspace discourse? In this research, we use the qualitative and quantitative method. First, we analyze the mechanism of linguistic construction of five jokes and their types and techniques based on Freud’s theory about this subject. Then we present the reactions produced by the jokes found in a social network and focus in the written representation of the laughter. The results show us that more women than men react to the jokes by writing a comment. The most popular laughter used by both men and women in a Spanish social network is "jajajaja" and the emoticon "XD". We have also found that people use the international laughter "hahahaha" and more women than men use "jejeje" to represent laughter in the same network. Although each individual has a laughter style, the way people represent the laughter graphically in the cyberspace discourse is almost the same between men and women but it differs in the way they use them as a reaction to the type and technique of the joke.

First-principle data-driven models for assessment of motor disorders in Parkinson’s disease

Parkinson’s disease (PD) is an increasing neurological disorder in an aging society. The motor and non-motor symptoms of PD advance with the disease progression and occur in varying frequency and duration. In order to affirm the full extent of a patient’s condition, repeated assessments are necessary to adjust medical prescription. In clinical studies, symptoms are assessed using the unified Parkinson’s disease rating scale (UPDRS). On one hand, the subjective rating using UPDRS relies on clinical expertise. On the other hand, it requires the physical presence of patients in clinics which implies high logistical costs. Another limitation of clinical assessment is that the observation in hospital may not accurately represent a patient’s situation at home. For such reasons, the practical frequency of tracking PD symptoms may under-represent the true time scale of PD fluctuations and may result in an overall inaccurate assessment. Current technologies for at-home PD treatment are based on data-driven approaches for which the interpretation and reproduction of results are problematic.  The overall objective of this thesis is to develop and evaluate unobtrusive computer methods for enabling remote monitoring of patients with PD. It investigates first-principle data-driven model based novel signal and image processing techniques for extraction of clinically useful information from audio recordings of speech (in texts read aloud) and video recordings of gait and finger-tapping motor examinations. The aim is to map between PD symptoms severities estimated using novel computer methods and the clinical ratings based on UPDRS part-III (motor examination). A web-based test battery system consisting of self-assessment of symptoms and motor function tests was previously constructed for a touch screen mobile device. A comprehensive speech framework has been developed for this device to analyze text-dependent running speech by: (1) extracting novel signal features that are able to represent PD deficits in each individual component of the speech system, (2) mapping between clinical ratings and feature estimates of speech symptom severity, and (3) classifying between UPDRS part-III severity levels using speech features and statistical machine learning tools. A novel speech processing method called cepstral separation difference showed stronger ability to classify between speech symptom severities as compared to existing features of PD speech. In the case of finger tapping, the recorded videos of rapid finger tapping examination were processed using a novel computer-vision (CV) algorithm that extracts symptom information from video-based tapping signals using motion analysis of the index-finger which incorporates a face detection module for signal calibration. This algorithm was able to discriminate between UPDRS part III severity levels of finger tapping with high classification rates. Further analysis was performed on novel CV based gait features constructed using a standard human model to discriminate between a healthy gait and a Parkinsonian gait. The findings of this study suggest that the symptom severity levels in PD can be discriminated with high accuracies by involving a combination of first-principle (features) and data-driven (classification) approaches. The processing of audio and video recordings on one hand allows remote monitoring of speech, gait and finger-tapping examinations by the clinical staff. On the other hand, the first-principles approach eases the understanding of symptom estimates for clinicians. We have demonstrated that the selected features of speech, gait and finger tapping were able to discriminate between symptom severity levels, as well as, between healthy controls and PD patients with high classification rates. The findings support suitability of these methods to be used as decision support tools in the context of PD assessment.

Monitoring vegetation on railway embankments : supporting maintenance decisions

The national railway administrations in Scandinavia, Germany, and Austria mainly resort to manual inspections to control vegetation growth along railway embankments. Manually inspecting railways is slow and time consuming. A more worrying aspect concerns the fact that human observers are often unable to estimate the true cover of vegetation on railway embankments. Further human observers often tend to disagree with each other when more than one observer is engaged for inspection. Lack of proper techniques to identify the true cover of vegetation even result in the excess usage of herbicides; seriously harming the environment and threating the ecology. Hence work in this study has investigated aspects relevant to human variationand agreement to be able to report better inspection routines. This was studied by mainly carrying out two separate yet relevant investigations.First, thirteen observers were separately asked to estimate the vegetation cover in nine imagesacquired (in nadir view) over the railway tracks. All such estimates were compared relatively and an analysis of variance resulted in a significant difference on the observers’ cover estimates (p<0.05). Bearing in difference between the observers, a second follow-up field-study on the railway tracks was initiated and properly investigated. Two railway segments (strata) representingdifferent levels of vegetationwere carefully selected. Five sample plots (each covering an area of one-by-one meter) were randomizedfrom each stratumalong the rails from the aforementioned segments and ten images were acquired in nadir view. Further three observers (with knowledge in the railway maintenance domain) were separately asked to estimate the plant cover by visually examining theplots. Again an analysis of variance resulted in a significant difference on the observers’ cover estimates (p<0.05) confirming the result from the first investigation.The differences in observations are compared against a computer vision algorithm which detects the "true" cover of vegetation in a given image. The true cover is defined as the amount of greenish pixels in each image as detected by the computer vision algorithm. Results achieved through comparison strongly indicate that inconsistency is prevalent among the estimates reported by the observers. Hence, an automated approach reporting the use of computer vision is suggested, thus transferring the manual inspections into objective monitored inspections

The influence of emotional contagion on products evaluation

Emotional Contagion is the mechanism that includes mimicking and the automatic synchronization of facial expressions, vocalizations, postures, and movements with another person and, consequently, convergence of emotions between the sender and receiver. Researches of this mechanism conducted usually in the fields of Psychology and Marketing tends to investigate face-to-face interactions. However, the question remains to what extent, if any, emotional contagion may occur with facial expressions in photos, since many purchase situations are brought on by catalogues or websites. This thesis has the goal to verify this gap and, in addition, verify whether emotional contagion is more common in females than in males as stated in previous studies. Emotions have been studied because it is intuitively apparent that emotions affect the dynamics of the interaction between a salesperson and customers (Verbeke, 1997); in other words, emotions may significantly affect consumer behavior. Therefore, this thesis also verified whether the facial expressions that transmit emotions could be associated to product evaluations. To investigate these questions, an experiment was done with 171 participants, which were exposed to either smiling (positive emotion) or neutral advertising. The differences between the individual advertisements were limited to the facial expressions of figures in the advertisements (either smiling or neutral/without smiling). One specialist and two students analyzed videotaped records of the participants’ responses, and found that participants who saw the positive stimulus mimicked the picture (smiling back) confirming the Emotional Contagion in Photos (the first hypothesis). The second hypothesis was to analyze if there is difference based in gender. The results demonstrated that there is not a significant difference between genders; female and male equally suffer Emotional Contagion. The third hypothesis was related to whether the positive emotions vs. neutral emotions acquired from the positive facial expression in the photo are associated to a positive evaluation of the product also displayed in the photo. Evidences show that the ad with a positive expression could change more positively the attitude, the sympathy, the reliability, and the intention of purpose of the participant compared to those who were exposed to the neutral condition. Therefore, the analysis concludes that the facial expressions displayed in photos produce emotional contagion and may interfere on the evaluation product. A discussion of the theoretical and practical implications and limitations for these findings are presented.

Color measurement using a smartphone applied to Madeira wines

Computer vision is a field that uses techniques to acquire, process, analyze and understand images from the real world in order to produce numeric or symbolic information in the form of decisions [1]. This project aims to use computer vision to prepare an app to analyze a Madeira Wine and characterize it (identify its variety) by its color. Dry or sweet wines, young or old wines have a specific color. It uses techniques to compare histograms in order to analyze the images taken from a test sample inside a special container designed for this purpose. The color analysis from a wine sample using an image captured by a smartphone can be difficult. Many factors affect the captured image such as, light conditions, the background of the sample container due to the many positions the photo can be taken (different to capture facing a white wall or facing the floor for example). Using new technologies such as 3D printing it was possible to create a prototype that aims to control the effect of those external factors on the captured image. The results for this experiment are good indicators for future works. Although it’s necessary to do more tests, the first tests had a success rate of 80% to 90% of correct results. This report documents the development of this project and all the techniques and steps required to execute the tests.

3D reconstruction through photographs

Humans can perceive three dimension, our world is three dimensional and it is becoming increasingly digital too. We have the need to capture and preserve our existence in digital means perhaps due to our own mortality. We have also the need to reproduce objects or create small identical objects to prototype, test or study them. Some objects have been lost through time and are only accessible through old photographs. With robust model generation from photographs we can use one of the biggest human data sets and reproduce real world objects digitally and physically with printers. What is the current state of development in three dimensional reconstruction through photographs both in the commercial world and in the open source world? And what tools are available for a developer to build his own reconstruction software? To answer these questions several pieces of software were tested, from full commercial software packages to open source small projects, including libraries aimed at computer vision. To bring to the real world the 3D models a 3D printer was built, tested and analyzed, its problems and weaknesses evaluated. Lastly using a computer vision library a small software with limited capabilities was developed.

Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

DANÇA: linguagem do corpo na educação infantil

This production is a reflection about the practices/experiences involving the teaching of the dance developed by the teachers in the Núcleo de Educação Infantil (NEI/UFRN), with the children from 2 to 7 years old, having as objectives: describe and interpret the lived experiences with the dance focusing on the meaning of the dance and organization of the pedagogic job, identify blanks in the pedagogic practices of dance and appoint possible perspectives to the teaching of dance on the infant education. The way from the investigation has begun with the following question: Who do the teachers understand the dance and live it on the Núcleo de Educação Infantil? The research of phenomenological orientation toke as methodological reference the qualitative approach from the placed phenomenon type, this one has as beginning the interest on the phenomenon by the way as it happens on the lived experience from where comes the knowledge with we can present about the world, trying to interpret it, understand it on its essence/existence. The interviews showed that the researched subjects give to the dance different meanings and consequently present variations on the manner to organize the work around this knowledge. The most of the teachers recognizes the dance as a culture expression, being a priority on the school the job with the folkloric dances. They recognize too the dance as knowledge/content coming from the Arts and Physical Education areas and its relation with the knowledge from others areas on the pedagogic action. There were found different process on the way to conduct the job with the dance in relates from experiences done with dance at NEI and, therefore, of teach/learn this knowledge. Its perceptible that exists a systematic work with the objective of develop the dance and its various educative possibilities, starting from the research about its origins, the exploration of the movement, the contextualization until the artistic practice. Those possibilities are reinforced on the school s curricular propose. Some experiences have as a priority the free expression, the dance s vision without context or the reproduction of movements as stand manners of teaching dance, situations like those observed on the investigation as products from the blanks on the academic formation from the teachers with must be fixed. The interpretation of the experiences with dance, described by the teachers from NEI, connected with the theoretical referential from the investigation, allowed to appoint three perspectives to the work with dance in the infant education, having as main interlocutors Merleau-Ponty and Rudolf Laban: the dance as the body s language; the dance and its movement factors; imitate, improvise and play: manners of draw ways to dance. On those process are emphasized the dance on the scholar context, the elements that constitute this language and the forms of appropriate from it supported in a ludicrous, poetic and educative vision, having as focus the children s education on its peculiarities and possibilities

Um sistema de visão para navegação robusta de uma plataforma robótica semi-autônoma

Large efforts have been maden by the scientific community on tasks involving locomotion of mobile robots. To execute this kind of task, we must develop to the robot the ability of navigation through the environment in a safe way, that is, without collisions with the objects. In order to perform this, it is necessary to implement strategies that makes possible to detect obstacles. In this work, we deal with this problem by proposing a system that is able to collect sensory information and to estimate the possibility for obstacles to occur in the mobile robot path. Stereo cameras positioned in parallel to each other in a structure coupled to the robot are employed as the main sensory device, making possible the generation of a disparity map. Code optimizations and a strategy for data reduction and abstraction are applied to the images, resulting in a substantial gain in the execution time. This makes possible to the high level decision processes to execute obstacle deviation in real time. This system can be employed in situations where the robot is remotely operated, as well as in situations where it depends only on itself to generate trajectories (the autonomous case)