01. Universidade Federal Rural de Pernambuco - UFRPE (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/1
Navegar
1 resultados
Resultados da Pesquisa
Item Detecção de mãos através da combinação de técnicas de detecção de tom de pele e movimento para background complexo(2018-08-18) Sá, Vinícius Cavalcanti Nogueira de; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/1197232523837982Technology has a social function to facilitate the life of its users, with its evolution, and with the emergence of globalization, the access to information and communication in general have become much more accessible for the general population. Nevertheless, groups with special needs still suffer from the lack of products and systems that can meet their needs. This work will make use of pre-existing technologies that can be used to make life easier for these users, especially deaf users. We live in a world where we are faced with an immensity of devices with cameras, or of equipment that can be connected to one, the computer vision becomes very important or otherwise, essential from this reality. Many areas use images to automate or assist their activities within their segments, whether they are for entertainment, industry or others. Thus, it is possible to realize the importance of image processing as a solution of problems in different areas. In this work it was used image processing to elaborate a possible solution in the hand recognition area, the use of the hand as a way of communication is evident. We can see it as a main character not only in everyday communication through gestures, but we can also use it in the control of computational interfaces, in the aid of immersion in virtual reality, in the manipulation of virtual objects in augmented reality or even as facilitator in the accessibility from the communication by signals, being this last example the key point of this work, that aims to facilitate the communication between deaf and possible users interested in the sign language through a new approach. Hand recognition was performed through a hybrid approach involving skin tone segmentation and movement, this approach was chosen to overcome the difficulties that each type of segmentation brings. The best hit rate we had with this approach was 76.4% indoors and 45.15% in outdoor environment.