English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

X-ray fluorescence spectroscopy (XRF) plays an important role for elementalanalysis in a wide range of scientific fields, especially in cultural heritage.XRF imaging, which uses a raster scan to acquire spectra across artworks,provides the opportunity for spatial analysis of pigment distributions based ontheir elemental composition. However, conventional XRF-based pigmentidentification relies on time-consuming elemental mapping by expertinterpretations of measured spectra. To reduce the reliance on manual work,recent studies have applied machine learning techniques to cluster similar XRFspectra in data analysis and to identify the most likely pigments.Nevertheless, it is still challenging for automatic pigment identificationstrategies to directly tackle the complex structure of real paintings, e.g.pigment mixtures and layered pigments. In addition, pixel-wise pigmentidentification based on XRF imaging remains an obstacle due to the high noiselevel compared with averaged spectra. Therefore, we developed adeep-learning-based end-to-end pigment identification framework to fullyautomate the pigment identification process. In particular, it offers highsensitivity to the underlying pigments and to the pigments with a lowconcentration, therefore enabling satisfying results in mapping the pigmentsbased on single-pixel XRF spectrum. As case studies, we applied our frameworkto lab-prepared mock-up paintings and two 19th-century paintings: PaulGauguin's Po\`emes Barbares (1896) that contains layered pigments with anunderlying painting, and Paul Cezanne's The Bathers (1899-1904). The pigmentidentification results demonstrated that our model achieved comparable resultsto the analysis by elemental mapping, suggesting the generalizability andstability of our model.

Can Deep Learning Assist Automatic Identification of Layered Pigments From XRF Data?