Detecção e rastreio de faces utilizando redes Bayesianas

• Ano de defesa: 2007
• Autor(a) principal: Candido, Jorge
• Orientador(a): Marengoni, Maurício
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Presbiteriana Mackenzie
• Palavras-chave em Português: redes Bayesianas; redes neurais; detecção de face
• Palavras-chave em Inglês: Bayesian networks; neural networks; face detection
• Área do conhecimento CNPq: CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: http://dspace.mackenzie.br/handle/10899/24365

This work presents a face detection system that uses a Bayesian Network to combine information from different computational cheap visual operators. The aim in this work is to show that combining simple features in a Bayesian Network allows building an enhanced face detector system, increasing the detection rate and speeding up the face detection process. This face detector has been developed to work in the stream acquired by a USB computer camera. After the detector finds a face in the stream, a face tracking system begins to work, locating the eyes position at the screen. The system is part of a high precision optical mouse system that will be used in human-computer interface, helpin users with certain disabilities.