Loading...
Publication
Natural interactions: an application for gestural hands recognition
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 3.19 MB | Adobe PDF |
Authors
Abstract(s)
Este trabalho apresenta um sistema para o desenvolvimento de novas interfaces homem-máquina com foco no reconhecimento de gestos estáticos de mãos humanas. A proposta é auxiliar o acesso a certos objetos para o ocupante de uma cadeira de rodas inteligente, a fim de facilitar a sua vida diária. A metodologia proposta baseia-se no uso de processos computacionais simples e de hardware de baixo custo. O seu desenvolvimento envolve uma abordagem completa aos problemas de visão computacional, com base nas etapas da captura de imagem de vídeo, segmentação de imagens, extração de características, reconhecimento e classificação de padrões. A importância deste trabalho relaciona-se com a necessidade de construir novos modelos de interação que permitam, de uma forma natural e intuitiva, a simplificação da vida quotidiana de uma pessoa com dificuldades motoras.
Abstract: This thesis presents a system for the development of new human-machine interfaces focused on static gestures recognition of human hands. The proposal is to give access to certain objects to the occupant of an intelligent wheelchair in order to facilitate their daily life. The proposed methodology relies on the use of simple computational processes and low-cost hardware. Its development involves a comprehensive approach to the problems of computer vision, based on the steps of the video image capture, image segmentation, feature extraction, pattern recognition and classification. The importance of this work relates to the need to build new models of interaction that allow, in a natural and intuitive way, to simplify the daily life of a disable person.
Abstract: This thesis presents a system for the development of new human-machine interfaces focused on static gestures recognition of human hands. The proposal is to give access to certain objects to the occupant of an intelligent wheelchair in order to facilitate their daily life. The proposed methodology relies on the use of simple computational processes and low-cost hardware. Its development involves a comprehensive approach to the problems of computer vision, based on the steps of the video image capture, image segmentation, feature extraction, pattern recognition and classification. The importance of this work relates to the need to build new models of interaction that allow, in a natural and intuitive way, to simplify the daily life of a disable person.
Description
Dissertação de Mestrado em Desenvolvimento de Software e Sistemas Interativos apresentada à Escola Superior de Tecnologia do Instituto Politécnico de Castelo Branco.
Keywords
Interação homem-máquina Reconhecimento de gestos Visão computacional Tecnologias assistivas Human-computer interaction Gesture recognition Computer vision Disable person Assistive technology