Desafios no uso de reconhecimento facial em sistemas de vídeo monitoramento no Brasil

• Ano de defesa: 2025
• Autor(a) principal: Reis, Sálvio Roberto Freitas
• Orientador(a): Vasconcelos, Rafael Oliveira
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Programa de Pós-Graduação: Pós-Graduação em Ciência da Computação
• Palavras-chave em Português: Reconhecimento facial; Privacidade; Desafios; Sistemas de videomonitoramento
• Palavras-chave em Inglês: Facial recognition; Privacy; Challenges; Video surveillance systems
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://ri.ufs.br/jspui/handle/riufs/22542

This dissertation addresses the challenges of using facial recognition in video surveillance systems in Brazil. Although widely adopted globally, this technology presents a series of specific complexities in the Brazilian context. The introduction contextualizes facial recognition as a tool of increasing importance for public and private security, highlighting its role in strengthening surveillance and its social impacts. However, as the technology expands, ethical, technical, and social issues arise that challenge its effective and fair implementation. This dissertation seeks to answer the following questions: what are the main challenges of these systems in Brazil? And how do these challenges compromise the reliability and public acceptance of the technology? The dissertation also discusses the ethical and social challenges associated with facial recognition, including the impact of monitoring on civil rights, such as privacy and individual freedom, as well as the public acceptance of this technology and the problem of disinformation. Cases of misuse, such as the criminalization of minorities, are analyzed in detail to illustrate the consequences of inadequate application or lack of robust regulations. In this sense, the analysis of case studies conducted in Brazilian states complements the discussion, offering a concrete perspective on the positive and negative impacts of technology in the national context. The methodology adopted included a systematic review of the academic literature. The results obtained integrate the challenges mapped with the experiences reported in the case studies. In the end, a series of recommendations are proposed that include the need for more robust regulations, the development of technological advances capable of reducing algorithmic biases, and the promotion of a more responsible and transparent use of facial recognition in Brazil. The aim is to ensure that the technology can be used in a simultaneously efficient and socially fair manner, meeting both security demands and contemporary ethical requirements.