Navegando por Autor "THEOCHAROPOULOS, Scarlette Silva"

Filtrar resultados informando as primeiras letras
Agora exibindo 1 - 2 de 2
  • Imagem de Miniatura
    Item
    Sistema Inteligente de Verificação de Pedidos com Visão Computacional e Aprendizado de Máquina para Expedição Industrial 4.0
    (Instituto de Tecnologia e Educação Galileo da Amazônia, 2025) THEOCHAROPOULOS, Scarlette Silva; SILVA, Maeli Oliveira da; CAMPOS, Paola Souto
    Certificate issued by the Brazilian National Institute of Industrial Property (INPI) for the registration of the computer program entitled Intelligent Order Verification System with Computer Vision and Machine Learning for Industrial 4.0 Shipping. Developed in Python, the software aims to optimize industrial processes by integrating computer vision algorithms and machine learning techniques to automate shipping in the context of Industry 4.0. The registration provides legal protection for 50 years under Law No. 9.609/1998, ensuring the proprietary rights of the authors and the holding institution over its technological application.
  • Imagem de Miniatura
    Item
    Sistema Inteligente de Verificação de Pedidos com Visão Computacional e Aprendizado de Máquina para Expedição Industrial 4.0
    (Instituto de Tecnologia e Educação Galileo da Amazônia, 2025) THEOCHAROPOULOS, Scarlette Silva; CAMPOS, Paola Souto
    This dissertation presents the development and evaluation of the PRS (Poligonal Reconnaissance System), designed for automated order verification in industrial environments within the context of Industry 4.0. The main objective was to develop an intelligent order verification system based on computer vision and machine learning, integrating image analysis, depth simulation, and hybrid validation (fixed rules and AI), with a focus on applications in automated shipment processes. The adopted methodology included the use of computer vision techniques to identify and calculate packaging areas in simulated images, depth simulation to correct perspective distortions, and a supervised Random Forest model trained with historical weight and area data. The resulting hybrid system demonstrated accuracy above 94% in detecting volume and weight inconsistencies, significantly reducing verification time and operational rework .