Open source face recognition API

• Autor(a) principal: Conceição, Diogo Neto Coxinho Mourisco da
• Data de Publicação: 2019
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/20307
• topic: Application; Algorithms; C++; Django; Framework; Image; Interface; JSON; Language; MySQL; Python; Programming; Recognition; Aplicação; Algoritmo; Imagem; Linguagem; Programação; Reconhecimento

Face recognition applications are widely used today for a variety of tasks, whether personal or professional. When looking for a service that provides face detection and classification, it is easy to find several solutions. In this project another way is described so that it is possible to perform this task according to the desired needs without the need to use proprietary software. With the emergence of the Django Rest Frame Work, web application development has become easier. This work describes development of stable foundation and features that offer an administration panel, relational database management, and support for a Restful Application Programming Interface (API). This takes advantage of the exclusive use of Open Source technologies thus the application code can be modified and distributed free of charge. For the development of an API that could perform detection and facial recognition, applying an Open Source philosophy, in addition to Django Rest Framework technologies such as Python, C++, MySql and JSON were used. The prototype is initially capable of recognizing the number of faces per image, assessing eyes, smile, age and gender. Flexibility is designed to increase application capabilities with new algorithms implemented in various programing languages.