Can deep learning assist automatic identification of layered pigments from XRF data?
Can deep learning assist automatic identification of layered pigments from XRF data?
复制标题
深度学习能否帮助从 XRF 数据中自动识别层状颜料？
DOI：
10.1039/d2ja00246a
复制
发表时间：
2022
影响因子：
3.4
通讯作者：
Willomitzer, Florian
中科院分区：
文献类型：
--
作者：
Xu, Bingjie Jenny;Wu, Yunan;Hao, Pengxiao;Vermeulen, Marc;McGeachy, Alicia;Smith, Kate;Eremin, Katherine;Rayner, Georgina;Verri, Giovanni;Willomitzer, Florian
X射线荧光光谱（XRF）在广泛的科学领域，特别是文化遗产中的元素分析中发挥着重要作用。XRF成像使用光栅扫描在艺术品上逐像素获取光谱，为基于元素组成的颜料分布空间分析提供了机会。然而，传统的基于XRF的颜料鉴定依赖于由专家对测量光谱的解释所促进的耗时的元素映射。为了减少对人工工作的依赖，最近的研究应用了机器学习技术，在数据分析中对相似的XRF光谱进行聚类，并识别最可能的颜料。然而，实现自动颜料识别策略以直接处理真实的绘画的复杂结构（例如，颜料混合物和分层颜料）仍然具有挑战性。此外，由于高噪声水平，基于XRF的逐像素颜料识别仍然是一个障碍。因此，我们开发了一个基于深度学习的色素识别框架，以完全自动化该过程。特别是，该方法对底层颜料和低浓度颜料具有高灵敏度，因此能够基于单像素XRF光谱对颜料进行稳健映射。作为案例研究，我们将我们的框架应用于实验室准备的模型绘画和两幅19世纪的绘画：Paul Gauguin的Poèmes Barbares（1896），其中包含分层颜料和底层绘画，以及Paul Cezanne的The Bathers（1899-1904）。色素的识别结果表明，我们的模型取得了可比的结果，通过元素映射分析，表明我们的模型的通用性和稳定性。
X-ray fluorescence spectroscopy (XRF) plays an important role for elemental analysis in a wide range of scientific fields, especially in cultural heritage. XRF imaging, which uses a raster scan to acquire spectra pixel-wise across artworks, provides the opportunity for spatial analysis of pigment distributions based on their elemental composition. However, conventional XRF-based pigment identification relies on time-consuming elemental mapping facilitated by the interpretation of measured spectra by experts. To reduce the reliance on manual work, recent studies have applied machine learning techniques to cluster similar XRF spectra in data analysis and to identify the most likely pigments. Nevertheless, it is still challenging to implement automatic pigment identification strategies to directly tackle the complex structure of real paintings, e.g. pigment mixtures and layered pigments. In addition, pigment identification based on XRF on a pixel-by-pixel basis remains an obstacle due to the high noise level. Therefore, we developed a deep-learning based pigment identification framework to fully automate the process. In particular, this method offers high sensitivity to the underlying pigments and to the pigments present in low concentrations, therefore enabling robust mapping of pigments based on single-pixel XRF spectra. As case studies, we applied our framework to lab-prepared mock-up paintings and two 19th-century paintings: Paul Gauguin's Poèmes Barbares (1896) that contains layered pigments with an underlying painting, and Paul Cezanne's The Bathers (1899–1904). The pigment identification results demonstrated that our model achieved comparable results to the analysis by elemental mapping, suggesting the generalizability and stability of our model.