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.

Multimodal automatic user disposition recognition in human-machine interaction

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013

Diseño centrado en el usuario y usabilidad en entorno táctil

En este trabajo se realiza un prototipo siguiendo un diseño centrado en el usuario, además se estudiaran los distintos tipos de pantallas táctiles que existen actualmente en el mercado y la forma de cómo conseguir una aplicación fácil y manejable.

Accessibilitat web : revisió d'accessibilitat del repositori documental de la UOC, Dspace

Aquest treball fi de carrera tracta sobre les normes d'accessibilitat WCAG 2.0 ("Web Content Accessibility Guidelines"). Són una sèrie de pautes i recomanacions per fer el contingut web més accessible, sobretot a una gamma més àmplia de persones amb discapacitat, com ceguesa i baixa visió, sordesa i la pèrdua d'audició, problemes d'aprenentatge, limitacions cognitives, limitacions de moviments, problemes de parla, fotosensibilitat i combinacions d'aquestes. Seguint aquestes directrius també fan sovint el contingut del seu web més usable per als usuaris en general.Les WCAG 2.0, recomanació oficial des del 11 de desembre de 2008, s'organitzen en 4 principis fonamentals per a l'accessibilitat del contingut: perceptible, operable, comprensible i robust.En total conformen 12 pautes o directrius (guidelines), els dos primers principis tenen quatre pautes associades, el tercer té tres i l'últim una pauta. Aquestes pautes proporcionen els objectius bàsics per fer el contingut accessible, i serveixen per comprendre els criteris d'èxit i implementar-los. S'han definit 60 criteris d'èxit o punts de comprovació que defineixen el nivell d'accessibilitat (A, AA o AAA).Per altra banda, s'analitzaran alternatives al programari que empra la UOC, Dspace, com a repositori de documentació. D'aquestes alternatives es valorarà sobretot l'aspecte d'accessibilitat per tal de determinar si l'elecció del Dspace ha estat l'opció més adient. També es s'analitzaran algunes planes del repositori de la UOC per tal de verificar el nivell de compliment de de les WCAG 2.0.Al mateix temps es farà una recerca d'eines que ens puguin ajudar en l'avaluació de l'accessibilitat i s'anomenaran en els punts que ens puguin ajudar cadascuna d'aquestes.

Developing and evaluating a pictogram-based Instant Messaging service for individuals with cognitive disabilities

Information and communication technologies pose accessibility problems to people with disabilities because its design fails to take into account their communication and usability requirements. The impossibility to access the services provided by these technologies creates a situation of exclusion that reduces the self-suficiency of disabled individuals and causes social isolation, which in turn diminishes their overall quality of life. Considering the importance of these technologies and services in our society, we have developed a pictogram-based Instant Messaging service for individuals with cognitive disabilities who have reading and writing problems. Along the paper we introduce and discuss the User Centred Design methodology that we have used to develop and evaluate the pictogram-based Instant Messaging service and client with individuals with cognitive disabilities taking into account their communication and usability requirements. From the results obtained in the evaluation process we can state that individuals with cognitive disabilities have been able to use the pictogram-based Instant Messaging service and client to communicate with their relatives and acquaintances, thus serving as a tool to help reducing their social and digital exclusion situation.

A Game to Promote Understanding about UCD Methods and Process

The User-centered design (UCD) game is a tool forhuman-computer interaction practitioners to demonstrate the key user-centered design methodsand how they interrelate in the design process in an interactive and participatory manner. The target audiences are departments and institutions unfamiliar with UCD but whose work is related to the definition, creation, and update of a product or service.

User-Centered Design Gymkhana

The User-centered design (UCD) Gymkhana is a tool for human-computer interaction practitioners to demonstrate through a game the key user-centered design methods and how they interrelate in the design process.The target audiences are other organizational departments unfamiliar with UCD but whose work is related to the definition, cretaion, and update of a product service.

A Three-Level Approach for Analyzing User Behavior in Ongoing Relationships

Peer-reviewed

A SOA-based Framework for Multi-Devices and Multi-Platform User Interfaces

This thesis reports investigations on applying the Service Oriented Architecture (SOA) approach in the engineering of multi-platform and multi-devices user interfaces. This study has three goals: (1) analyze the present frameworks for developing multi-platform and multi-devices applications, (2) extend the principles of SOA for implementing a multi-platform and multi-devices architectural framework (SOA-MDUI), (3) applying and validating the proposed framework in the context of a specific application. One of the problems addressed in this ongoing research is the large amount of combinations for possible implementations of applications on different types of devices. Usually it is necessary to take into account the operating system (OS), user interface (UI) including the appearance, programming language (PL) and architectural style (AS). Our proposed approach extended the principles of SOA using patterns-oriented design and model-driven engineering approaches. Synthesizing the present work done in these domains, this research built and tested an engineering framework linking Model-driven Architecture (MDA) and SOA approaches to developing of UI. This study advances general understanding of engineering, deploying and managing multi-platform and multi-devices user interfaces as a service.

Eye tracking and gaze based interaction within immersive virtual environments

Our eyes are input sensors which Provide our brains with streams of visual data. They have evolved to be extremely efficient, and they will constantly dart to-and-fro to rapidly build up a picture of the salient entities in a viewed scene. These actions are almost subconscious. However, they can provide telling signs of how the brain is decoding the visuals and call indicate emotional responses, prior to the viewer becoming aware of them. In this paper we discuss a method of tracking a user's eye movements, and Use these to calculate their gaze within an immersive virtual environment. We investigate how these gaze patterns can be captured and used to identify viewed virtual objects, and discuss how this can be used as a, natural method of interacting with the Virtual Environment. We describe a flexible tool that has been developed to achieve this, and detail initial validating applications that prove the concept.

An agent based approach to distributed task modeling for co-operative task support

This paper describes the design and implementation of an agent based network for the support of collaborative switching tasks within the control room environment of the National Grid Company plc. This work includes aspects from several research disciplines, including operational analysis, human computer interaction, finite state modelling techniques, intelligent agents and computer supported co-operative work. Aspects of these procedures have been used in the analysis of collaborative tasks to produce distributed local models for all involved users. These models have been used as the basis for the production of local finite state automata. These automata have then been embedded within an agent network together with behavioural information extracted from the task and user analysis phase. The resulting support system is capable of task and communication management within the transmission despatch environment.