2025-08-252025-08-252025-07-08FERREIRA, Gabriel Lima. Viabilidade técnica de um sistema de OCR para monitoramento de sinais vitais em monitores multiparâmetro. Orientador: Rafael Suzuki Bayma. 2025. 81 f. Trabalho de Conclusão de Curso (Bacharelado em Engenharia Elétrica) – Faculdade de Engenharia Elétrica, Campus Universitário de Tucuruí, Universidade Federal do Pará, Tucuruí, 2025. Disponível em: https://bdm.ufpa.br/handle/prefix/8504. Acesso em:.https://bdm.ufpa.br/handle/prefix/8504This work presents the development and evaluation of a Python-based system leveraging computer vision (OpenCV) and OCR (Pytesseract) techniques for automated extraction of vital signs from medical monitor videos. Four videos obtained online—with varying resolutions, frame rates, and lighting conditions—were processed to assess the method’s sensitivity to external factors. The oxygen saturation region achieved accuracies between 94 % and 100 %, while heart rate ranged from 69.23 % to 100 %. Pulse rate extraction showed greater dispersion, from only 2.86 % in the first video to 100 % after subsequent adjustments. The overall mean accuracy was 84.29 % (mean error of 15.71 %), demonstrating the technical feasibility of the system. The main limitations identified relate to video quality—resolution, camera stability, illumination, and visual noise—underscoring the need for controlled environments and fine-tuned ROI calibration. This technical feasibility study shows that combining OpenCV and Pytesseract can support remote monitoring solutions in intensive care units, provided minimum image capture conditions are met.Acesso AbertoVisão computacionalOCRMonitoramento de sinais vitaisViabilidade técnicaComputer visionVital signs monitoringTechnical feasibilityCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAOCNPQ::ENGENHARIAS::ENGENHARIA BIOMEDICA::BIOENGENHARIA::PROCESSAMENTO DE SINAIS BIOLOGICOSTrabalho de Curso - Graduação - MonografiaAttribution-NonCommercial-NoDerivs 3.0 Brazil