Publicação
Age and gender classification: A proposed system
| Resumo: | With the new General Data Protection Regulation, there has been a lot of concerns when it comes to saving personal and sensitive data. As a result, there is a necessity to gather information without storing any data that could be considered sensitive, and that could identify the person to which it belongs to. Our motivation was to create a system that could be used to gather information about the people that visit commercial areas, using their surveillance systems as input to the application. In the present work, we developed a system capable of gathering age and gender information from people based on images, using Deep Learning. Such system was built using a face detection model based on the GoogLeNet deep neural network and on a Wide Residual Network for age and gender classification, supported by a Siamese Network for the latter. The outcome is, to the best of our knowledge, the first available implementation that makes use of Wide Residual Networks and Siamese Networks at the same time for gender classification. |
|---|---|
| Autores principais: | Silva, David Pereira da |
| Assunto: | Face detection Deep learning Convolutional neural network Gender prediction Artificial intelligence Age classification Detecção de faces Redes neuronais convolucionais Previsão de género Inteligência artificial Classificação por idade Vigilância electrónica Método de detecção Redes neuronais Segurança da informação Proteção dos dados |
| Ano: | 2019 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | ISCTE |
| Idioma: | inglês |
| Origem: | Repositório ISCTE |
| Resumo: | With the new General Data Protection Regulation, there has been a lot of concerns when it comes to saving personal and sensitive data. As a result, there is a necessity to gather information without storing any data that could be considered sensitive, and that could identify the person to which it belongs to. Our motivation was to create a system that could be used to gather information about the people that visit commercial areas, using their surveillance systems as input to the application. In the present work, we developed a system capable of gathering age and gender information from people based on images, using Deep Learning. Such system was built using a face detection model based on the GoogLeNet deep neural network and on a Wide Residual Network for age and gender classification, supported by a Siamese Network for the latter. The outcome is, to the best of our knowledge, the first available implementation that makes use of Wide Residual Networks and Siamese Networks at the same time for gender classification. |
|---|