Skip to main content

A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs

Publication ,  Conference
Pu, W; Huang, J; Sober, B; Daly, N; Higgitt, C; Dragotti, PL; Daubechies, I; Rodrigues, MRD
Published in: European Signal Processing Conference
January 1, 2021

X-ray images are widely used in the study of paintings. When a painting has hidden sub-surface features (e.g., reuse of the canvas or revision of a composition by the artist), the resulting X-ray images can be hard to interpret as they include contributions from both the surface painting and the hidden design. In this paper we propose a self-supervised deep learning-based image separation approach that can be applied to the X-ray images from such paintings ('mixed X-ray images') to separate them into two hypothetical X-ray images, one containing information related to the visible painting only and the other containing the hidden features. The proposed approach involves two steps: (1) separation of the mixed X-ray image into two images, guided by the combined use of a reconstruction and an exclusion loss; (2) even allocation of the error map into the two individual, separated X-ray images, yielding separation results that have an appearance that is more familiar in relation to X-ray images. The proposed method was demonstrated on a real painting with hidden content, Doña Isabel de Porcel by Francisco de Goya, to show its effectiveness.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

European Signal Processing Conference

DOI

ISSN

2219-5491

ISBN

9789082797060

Publication Date

January 1, 2021

Volume

2021-August

Start / End Page

1491 / 1495
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Pu, W., Huang, J., Sober, B., Daly, N., Higgitt, C., Dragotti, P. L., … Rodrigues, M. R. D. (2021). A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs. In European Signal Processing Conference (Vol. 2021-August, pp. 1491–1495). https://doi.org/10.23919/EUSIPCO54536.2021.9616096
Pu, W., J. Huang, B. Sober, N. Daly, C. Higgitt, P. L. Dragotti, I. Daubechies, and M. R. D. Rodrigues. “A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs.” In European Signal Processing Conference, 2021-August:1491–95, 2021. https://doi.org/10.23919/EUSIPCO54536.2021.9616096.
Pu W, Huang J, Sober B, Daly N, Higgitt C, Dragotti PL, et al. A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs. In: European Signal Processing Conference. 2021. p. 1491–5.
Pu, W., et al. “A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs.” European Signal Processing Conference, vol. 2021-August, 2021, pp. 1491–95. Scopus, doi:10.23919/EUSIPCO54536.2021.9616096.
Pu W, Huang J, Sober B, Daly N, Higgitt C, Dragotti PL, Daubechies I, Rodrigues MRD. A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs. European Signal Processing Conference. 2021. p. 1491–1495.

Published In

European Signal Processing Conference

DOI

ISSN

2219-5491

ISBN

9789082797060

Publication Date

January 1, 2021

Volume

2021-August

Start / End Page

1491 / 1495