Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"

Generic system for human-computer gesture interaction: applications on sign language recognition and robotic soccer refereeing

Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer vision and machine learning, able to be used with any interface for human-computer interaction. The proposed solution is mainly composed of three modules: a pre-processing and hand segmentation module, a static gesture interface module and a dynamic gesture interface module. The experiments showed that the core of visionbased interaction systems could be the same for all applications and thus facilitate the implementation. For hand posture recognition, a SVM (Support Vector Machine) model was trained and used, able to achieve a final accuracy of 99.4%. For dynamic gestures, an HMM (Hidden Markov Model) model was trained for each gesture that the system could recognize with a final average accuracy of 93.7%. The proposed solution as the advantage of being generic enough with the trained models able to work in real-time, allowing its application in a wide range of human-machine applications. To validate the proposed framework two applications were implemented. The first one is a real-time system able to interpret the Portuguese Sign Language. The second one is an online system able to help a robotic soccer game referee judge a game in real time.

Vision-based portuguese sign language recognition system

Vision-based hand gesture recognition is an area of active current research in computer vision and machine learning. Being a natural way of human interaction, it is an area where many researchers are working on, with the goal of making human computer interaction (HCI) easier and natural, without the need for any extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them, for example, to convey information. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. Hand gestures are a powerful human communication modality with lots of potential applications and in this context we have sign language recognition, the communication method of deaf people. Sign lan- guages are not standard and universal and the grammars differ from country to coun- try. In this paper, a real-time system able to interpret the Portuguese Sign Language is presented and described. Experiments showed that the system was able to reliably recognize the vowels in real-time, with an accuracy of 99.4% with one dataset of fea- tures and an accuracy of 99.6% with a second dataset of features. Although the im- plemented solution was only trained to recognize the vowels, it is easily extended to recognize the rest of the alphabet, being a solid foundation for the development of any vision-based sign language recognition user interface system.

An integrated system for human action recognition from video using hidden Markov model

In this paper, we present an integrated system for real-time automatic detection of human actions from video. The proposed approach uses the boundary of humans as the main feature for recognizing actions. Background subtraction is performed using Gaussian mixture model. Then, features are extracted from silhouettes and Vector Quantization is used to map features into symbols (bag of words approach). Finally, actions are detected using the Hidden Markov Model. The proposed system was validated using a newly collected real- world dataset. The obtained results show that the system is capable of achieving robust human detection, in both indoor and outdoor environments. Moreover, promising classification results were achieved when detecting two basic human actions: walking and sitting.

Enrollment time as a requirement for biometric hand recognition systems

Biometric systems are increasingly being used as a means for authentication to provide system security in modern technologies. The performance of a biometric system depends on the accuracy, the processing speed, the template size, and the time necessary for enrollment. While much research has focused on the first three factors, enrollment time has not received as much attention. In this work, we present the findings of our research focused upon studying user’s behavior when enrolling in a biometric system. Specifically, we collected information about the user’s availability for enrollment in respect to the hand recognition systems (e.g., hand geometry, palm geometry or any other requiring positioning the hand on an optical scanner). A sample of 19 participants, chosen randomly apart their age, gender, profession and nationality, were used as test subjects in an experiment to study the patience of users enrolling in a biometric hand recognition system.

Reflexão crítica sobre a redução das pensões no âmbito da convergência dos regimes da Caixa Geral de Aposentações e da Segurança Social

Dissertação de mestrado em Direito Tributário e Fiscal

Effects of forest structure components on the occurence, group size and density of groups of bare-face tamarin (Saguinus bicolor - primates: Callitrichinae) in Central Amazonia

This study analyzed the influence of forest structural components on the occurence, size and density of groups of Bare-face Tamarin (Saguinus bicolor) - the most threatened species in the Amazon - and produced the first map of distribution of groups in large-scale spatial within the area of continuous forest. Population censuses were conducted between November 2002 and July 2003, covering 6400 hectares in the Ducke Reserve, Manaus-AM, Brazil. Groups of S. bicolor were recorded 41 times accordingly distributed in the environments: plateau (20); slopes (12); and lowlands (09). The mean group size was 4.8 indiv./group, and ranged from 2 to 11 individuals. In the sites where the groups were recorded, and in an equivalent number of sites where no tamarins were found located at least 500 m from those where they had been recorded, we placed 50 m x 50 m plots to record the following forest structural components: abundance of trees; abundance of lianas; abundance of fruiting trees and lianas; abundance of snags; abundance of logs; percentage of canopy opening; leaf litter depth; and altitude. Bare-face Tamarin more often uses areas with lower abundance of forest logs, smaller canopy opening and with higher abundance of snags, areas in the forest with smaller canopy opening present higher density of S. bicolor groups. Apparently this species does not use the forest in a random way, and may select areas for its daily activities depending on the micro-environmental heterogeneity produced by the forest structural components.

Neural correlates of face familiarity in institutionally reared children with distinctive, atypical social behavior

Although the impact of early adverse experience on neural processing of face familiarity has been studied, research has not taken into account disordered child behavior. This work compared the neural processing of familiar versus strangers' faces in 47 institutionalized children with a mean age of 54 months to determine the effects of (a) the presence versus absence of atypical social behavior and (b) inhibited versus indiscriminant atypical behavior. Results revealed a pattern of cortical hypoactivation in institutionalized children manifesting atypical social behavior and that inhibited children displayed larger neural response to a caregiver's face than to the stranger's, while indiscriminant children did not discriminate between stimuli. These findings suggest that neural correlates of face familiarity are associated with social functioning in institutionalized children.

O efeito da adição de 40% de cinzas volantes sobre o ingresso de cloretos no betão face à ação combinada entre a carbonatação e os iões cloreto

Além de imprimir um caráter sustentável ao betão, as cinzas volantes (CV) têm sido bastante utilizadas para tornar a matriz cimentícia mais resistente à penetração de Cl-uma vez que tornam a estrutura porosa mais densa e ajudam a fixar Cl-. Por outro lado, sabe-se que o Ca(OH)2 existente na matriz é parcialmente consumido pelas reações pozolânicas, facilitando o avanço da carbonatação e, consequentemente, aumentando a quantidade de Cl-livres. Considerando a ação conjunta destes agentes, especula-se sobre o papel das CV na penetração de Cl-. Foram moldados provetes com 0% e 40% de CV. Após 90 dias de cura os provetes foram submetidos a 12 ciclos de imersão em solução com NaCl e secagem em câmara de carbonatação , num total de 168 dias. Observou-se que os provetes contendo CV, e submetidos à ação combinada, apresentaram perfis de Cl-com teores superiores quando comparados à ação exclusiva dos Cl.

Estudo acústico de /a/ acentuado na fala bracarense: potenciais aplicações

Dissertação de mestrado em Ciências da Linguagem

Patterns of Mycobacterium tuberculosis-complex excretion and characterization of super-shedders in naturally-infected wild boar and red deer

Wild boar (Sus scrofa) and red deer (Cervus elaphus) are the main maintenance hosts for bovine tuberculosis (bTB) in continental Europe. Understanding Mycobacterium tuberculosis complex (MTC) excretion routes is crucial to define strategies to control bTB in free-ranging populations, nevertheless available information is scarce. Aiming at filling this gap, four different MTC excretion routes (oronasal, bronchial-alveolar, fecal and urinary) were investigated by molecular methods in naturally infected hunter-harvested wild boar and red deer. In addition MTC concentrations were estimated by the Most Probable Number method. MTC DNA was amplified in all types of excretion routes. MTC DNA was amplified in at least one excretion route from 83.0% (CI95 70.8-90.8) of wild ungulates with bTB-like lesions. Oronasal or bronchial-alveolar shedding were detected with higher frequency than fecal shedding (p < 0.001). The majority of shedders yielded MTC concentrations <10(3) CFU/g or mL. However, from those ungulates from which oronasal, bronchial-alveolar and fecal samples were available, 28.2% of wild boar (CI95 16.6-43.8) and 35.7% of red deer (CI95 16.3-61.2) yielded MTC concentrations >10(3) CFU/g or mL (referred here as super-shedders). Red deer have a significantly higher risk of being super-shedders compared to wild boar (OR = 11.8, CI95 2.3-60.2). The existence of super-shedders among the naturally infected population of wild boar and red deer is thus reported here for the first time and MTC DNA concentrations greater than the minimum infective doses were estimated in excretion samples from both species.

Impact of health legislation on the sale of anorectics in a city in the Amazon region

OBJECTIVES: The International Narcotics Control Board released its 2005 annual report, highlighting the Brazil population as one of the largest consumers of anorectics. In Brazil, the National Health Surveillance Agency issued the resolution RDC 58/2007 in order to control the prescription and sale of such drugs. In Belém, the biggest city in the Brazilian Amazon region, this resolution came into force in 2008, leading to inspections of drugstores and magistral pharmacies. The aim of this work was to evaluate the consumption of psychotropic anorectic drugs and the impact of RDC 58/2007 on the prescription and dispensing of anorectics in drugstores and magistral pharmacies in Belém. METHODOLOGY: A retrospective quantitative and descriptive study was conducted of records from the Municipal Department of Health Surveillance of Belém, for 2005 to 2008. The differences in findings were regarded significant when p < 0.05. RESULTS: A total of 1,641 balance sheets of drugstores and magistral pharmacies were analyzed. Amfepramone was the most dispensed medication, followed by fenproporex and mazindol. The highest consumption of anorectics occurred in magistral pharmacies. In 2008, there was a significant reduction in dispensing of anorectics, in drugstores as well as in magistral pharmacies. CONCLUSIONS: This study showed that there was a decrease in the dispensing of anorectics after RDC 58/2007 came into force, and that the magistral pharmacies dispensed more of these drugs. This resolution is a remarkable tool in health control, where it is of great benefit to public health and contributes substantially to the rational use of medicines in Brazil.

Estudo exploratório sobre as concepções e estratégias de intervenção de professores em face do bullying escolar

Este estudo qualitativo objetivou identificar o conhecimento de professores do 6º ano do ensino fundamental sobre o bullying e as intervenções por eles desenvol- vidas. Participaram dez professores, e os dados foram coletados por meio de questio- nários estruturados. As análises seguiram os pressupostos da análise de conteúdo, em sua modalidade temática. Verificou-se, nos resultados, uma compreensão insuficiente dos professores que incidia na capacidade de identificação e na maneira como intervi- nham nos episódios de bullying entre os alunos. Depreende-se que o bullying constitui um aspecto importante a ser trabalhado com os professores, considerando a proximi- dade com a questão e o papel essencial que podem assumir no seu enfrentamento.

The mineralogy and chemistry of the German and Portuguese tiles used to face a historic building in the Amazon region and their natural susceptibility to tropical weathering

During the 19th century, the most prominent buildings of the city of Belém were faced entirely with tiles manufactured in Portugal and Germany, which now exhibit distinct degrees of degradation. The Pinho mansion is one of the most important of these buildings and was selected for the investigation of the action of the tropical Amazonian climate on the degradation of the tiles. To achieve this objective, the tiles were mapped for organic and inorganic degradation, and samples were collected for analysis. The minerals were determined by XRD, the chemical composition by classical wet methods and SEM/EDS, and the microorganisms under the microscope. The results show that the German and Portuguese tiles are quite different in their composition. While both ceramic bodies are composed of SiO2 and Al2O3, CaO was found only in the Portuguese tile. The low Na2O and K2O contents indicate the addition of materials to reduce the fusion temperature. SiO2 and PbO are the main constituents of the glaze, with CoO and FeO being added as pigment. The ceramic body of the German tiles is constituted of quartz, mullite, and cristobalite, in contrast with the Portuguese tiles, which are made of quartz, gehlenite, diopside, calcite, and feldspars. The glazes are XRD-amorphous. The chemical and mineralogical differences between the German and Portuguese tiles indicate that they were produced from different raw materials under distinct thermal processes. The most prominent weathering-related modifications are the thin layers (German tiles), oxidation stains, dark stains, the detachment of the tile (Portuguese tiles), loss of the glaze and powdering of the ceramic body (Portuguese tiles) through the establishment of Cyanophyta and Bacillariophyta.. The distinct degradation patterns of the tiles exposed to the tropical Amazon climate are a consequence of their distinct mineralogy and chemistry.

Evaluation of geostatistical techniques to estimate the spatial distribution of aboveground biomass in the Amazon rainforest using high-resolution remote sensing data

ABSTRACT The spatial distribution of forest biomass in the Amazon is heterogeneous with a temporal and spatial variation, especially in relation to the different vegetation types of this biome. Biomass estimated in this region varies significantly depending on the applied approach and the data set used for modeling it. In this context, this study aimed to evaluate three different geostatistical techniques to estimate the spatial distribution of aboveground biomass (AGB). The selected techniques were: 1) ordinary least-squares regression (OLS), 2) geographically weighted regression (GWR) and, 3) geographically weighted regression - kriging (GWR-K). These techniques were applied to the same field dataset, using the same environmental variables derived from cartographic information and high-resolution remote sensing data (RapidEye). This study was developed in the Amazon rainforest from Sucumbíos - Ecuador. The results of this study showed that the GWR-K, a hybrid technique, provided statistically satisfactory estimates with the lowest prediction error compared to the other two techniques. Furthermore, we observed that 75% of the AGB was explained by the combination of remote sensing data and environmental variables, where the forest types are the most important variable for estimating AGB. It should be noted that while the use of high-resolution images significantly improves the estimation of the spatial distribution of AGB, the processing of this information requires high computational demand.