Publication: Identificación de imágenes por análisis de texturas utilizando aprendizaje automático
Loading...
Official URL
Full text at PDC
Publication Date
2020
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Citations
Exportar
Abstract
Hoy en día, el tratamiento y reconocimiento de imágenes gracias a la inteligencia artificial y análisis de estas mediante aprendizaje automático nos reporta enormes beneficios y aplicaciones en el mundo moderno. A partir de estos mecanismos podemos pilotar vehículos de manera autónoma, reconocer expresiones o detectar enfermedades mediante el entrenamiento, refuerzo y test de la máquina.
Concretamente nuestro proyecto está dirigido al procesamiento digital mediante aprendizaje automático empleado para el análisis de texturas. A medida que avancemos en la lectura y desarrollo de esta memoria detallaremos sobre los métodos empleados, finalidad y objetivos del proyecto.
En términos generales, la finalidad última es desarrollar una máquina capaz de clasificar texturas a partir de una serie de imágenes de radiografías de la caja torácica que incluye mayormente los pulmones, con el motivo de detectar enfermedades respiratorias como la neumonía.
Para ello hemos dividido el proyecto en diversas fases debidamente diferenciadas:
-Investigación y trabajo previo.
-Implementación y desarrollo del programa.
-Módulos 1, 2 y 3
-Pruebas y evaluación sobre imágenes torácicas de rayos-x con neumonía asociada al SARS-CoV-2.
-Síntesis y resultados finales.
Today, the treatment and recognition of images thanks to artificial intelligence and the analysis of these through machine learning report the benefits and applications in the modern world. From these mechanisms we can pilot vehicles autonomously, recognize expressions or detect diseases through training, reinforcement and testing of the machine. Specifically, our project is aimed at digital processing through machine learning used for the analysis of textures. As we continue reading and developing this report, we will detail the methods used, purposes and objectives of the project. In general terms, the last one is a machine capable of classifying textures from a series of x-ray images of the rib cage that mainly includes the lungs, in order to detect respiratory diseases such as pneumonia. To do this, we have divided the project into various different phases: -Investigation and previous work. -Implementation and development of the program. -Modules 1, 2 and 3 -Testing and evaluation with torax x-ray images of pneumonia associated to SARS-CoV-2. -Synthesis and final results.
Today, the treatment and recognition of images thanks to artificial intelligence and the analysis of these through machine learning report the benefits and applications in the modern world. From these mechanisms we can pilot vehicles autonomously, recognize expressions or detect diseases through training, reinforcement and testing of the machine. Specifically, our project is aimed at digital processing through machine learning used for the analysis of textures. As we continue reading and developing this report, we will detail the methods used, purposes and objectives of the project. In general terms, the last one is a machine capable of classifying textures from a series of x-ray images of the rib cage that mainly includes the lungs, in order to detect respiratory diseases such as pneumonia. To do this, we have divided the project into various different phases: -Investigation and previous work. -Implementation and development of the program. -Modules 1, 2 and 3 -Testing and evaluation with torax x-ray images of pneumonia associated to SARS-CoV-2. -Synthesis and final results.
Description
Trabajo de Fin de Grado en Ingeniería Informática, Facultad de Informática UCM, Departamento de Arquitectura de Computadores y Automática, Curso 2019/2020