Examinando por Materia "Pattern recognition"

Mostrando 1 - 5 de 5
  • No hay miniatura disponible
    Ítem
    Desarrollo de librería para manejo de redes neuronales en Java para tecnofactor
    (Universidad EAFIT, 2019) Arboleda Echeverry, Juan Camilo; Rincón Bermúdez, Rafael David
    The aim of the present project is to design and develop a working library that enables the creation and adaptation of Neural Networks, defined in a way that is simple to use by Java developers. The developed library will be used to design and obtain a neural network capable of recognizing handwritten digits, from the MNIST database.
  • No hay miniatura disponible
    Publicación
    ROC-ME reconocimiento óptico de caracteres en medidores de energía
    (Universidad EAFIT, 2021) Mejía Quintero, Camila; Quintero Montoya, Olga Lucía
  • No hay miniatura disponible
    Ítem
    Short Research Advanced Project: Development of Strategies for Automatic Facial Feature Extraction and Emotion Recognition
    (IEEE, 2017-10-18) Restrepo, David; Gomez, Alejandro; Restrepo, David; Gomez, Alejandro; Universidad EAFIT. Departamento de Ciencias; Modelado Matemático
    Emotions are a fundamental part of the personal and social skills of the human being. The behavior, intelligence, reason and decision making process are some of the topic that can be influenced by the emotional state of a person. In this paper we develop a computational way for emotion recognition though images using the Cohn-Kanade database to train a pattern recognition neural network and Viola Jones object detector to extract the information of the facial expression. The resulting neural network showed an overall accuracy of 90.7% in recognizing between 6 basic emotions such a surprise, fear, happiness, sadness, disgust and anger.
  • No hay miniatura disponible
    Publicación
    Spatial epidemic patterns recognition using computer algebra
    (SPRINGER, 2007-01-01) Hincapié, D.; Ospina, J.; Universidad EAFIT. Departamento de Ciencias; Lógica y Computación
    An exploration in Symbolic Computational bio-surveillance is showed. The main obtained results are that the geometry of the habitat determines the critical parameters via the zeroes of the Bessel functions and the explicit forms of the static and non-static spatial epidemic patterns. © Springer-Verlag Berlin Heidelberg 2007.
  • No hay miniatura disponible
    Ítem
    Use of optical vortices for the compression of fingerprint recognition systems
    (IOP PUBLISHING LTD, 2017-06-13) Martín R.-V.; René R.; Universidad EAFIT. Departamento de Ciencias Básicas; Óptica Aplicada
    In this article, an algorithm is presented for the processing and verification of fingerprints by analyzing optical vortices present in the orientation of the fringes of the fingerprint. The algorithm presents a compression factor of 1200, but is highly susceptible to the presence of noise. © Published under licence by IOP Publishing Ltd.