Crack Detection in Oil Paintings Using Morphological Filters and K-SVD Algorithm

Carla Rucoba-Calderón, Efrain Ramos, Juan Gutiérrez-Cárdenas

Resultado de la investigación: Capítulo del libro/informe/acta de congresoCapítulo

Resumen

Cracks in oil paintings constitute an undesirable but unavoidable effect of time, deteriorating the painting quality. This work proposes a crack detection method that supports the physical restoration process of the artworks, providing a fissure map that allows the artist to visualize the pictorial layer and its flaws. This approach applies three image processing techniques to digitized oil paintings: oriented elongated filters, top-hat morphological filters and a K-SVD algorithm. Then, a post-processing stage based on K-Means is performed on the resulting binary maps to eliminate false positives. Finally, a pixel-by-pixel voting technique is applied to combine the binary maps. Our proposed framework has a better performance detecting craquelure when compared to other methods such as ADA Boost and convolutional neural networks. We obtained a recall of 0.8577, a probability of false alarm of 0.0779, a probability of false negatives of 0.1423, an accuracy of 0.7123, and an F1 value of 0.7783, which is amongst the best results for the state-of-the-art techniques.

Idioma originalInglés
Título de la publicación alojadaCommunications in Computer and Information Science
EditoresJuan Antonio Lossio-Ventura, Jorge Valverde-Rebaza, Eduardo Díaz, Denisse Muñante, Carlos Gavidia-Calderon, Alan Demétrius Valejo, Hugo Alatrista-Salas
EditorialSpringer Science and Business Media Deutschland GmbH
Páginas329-339
Número de páginas11
ISBN (versión impresa)9783031044465
DOI
EstadoPublicada - 1 ene. 2022
Evento8th Annual International Conference on Information Management and Big Data, SIMBig 2021 - Virtual, Online
Duración: 1 dic. 20213 dic. 2021

Serie de la publicación

NombreCommunications in Computer and Information Science
Volumen1577 CCIS

Conferencia

Conferencia8th Annual International Conference on Information Management and Big Data, SIMBig 2021
CiudadVirtual, Online
Período1/12/213/12/21

COAR

  • Artículo

Huella

Profundice en los temas de investigación de 'Crack Detection in Oil Paintings Using Morphological Filters and K-SVD Algorithm'. En conjunto forman una huella única.

Citar esto