Detection of Deteriorated Sections in Murals using Machine Learning

Descripción:

The detection of deteriorated sections in ancient murals has posed a significant challenge due to the wear caused by natural and human factors. In recent decades, various methods have been developed to address this problem, ranging from manual techniques to automated approaches. This article presents an analysis to identify deteriorated areas in historical murals, specifically generative adversarial networks (GANs), convolutional neural networks (CNN), U-Net, and K-Nearest Neighbors (KNN). We evaluate the effectiveness in different contexts of deterioration, highlighting their advantages and limitations to assist in the conservation of murals.

Tipo de publicación: Conference Paper

Publicado en: 2024 IEEE VII Congreso Internacional en Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC)

Autores
  • Valdés, José Longino Mendoza
  • Quesada-López, Christian
  • Lara, Adrian

Investigadores del CITIC asociados a la publicación
Dr. Christian Quesada-López
Dr. Adrian Lara Petitdemange

Proyecto asociado a la publicación

DOI BIBTEXT

Datos bibliográficos
Cita bibliográfica
Detection of Deteriorated Sections in Murals using Machine Learning