Hierarchical clustering as an unsurpervised machine learning algorithm for hyperspectral image segmentation of films

Liu, Lingxi; Delnevo, Giovanni; Mirri, Silvia

doi:10.1145/3524458.3547124

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A range of cutting-edge data processing techniques has particularly been applied in the CH domain to reduce the dimensionality of the dataset, classify and unmix spectral signature to map paint components. Thus, numerous approaches were developed, starting from the conventional multivariate analyses and statistical methods (e.g., spectral angle mapper (SAM) [10][11][12][13], fully constrained least square (FCLS) [14][15][16], principal component analyses (PCA) [17][18][19][20], minimum noise fraction transform (MNF) [21,22], and k-means clustering [23][24][25]), to the more advanced machine learning algorithms (support vector machine (SVM) [26,27], hierarchical clustering [28], embedding techniques [29][30][31][32], MaxD [11,24,33], dictionary learning [34,35]) with a growing interest for neural network algorithms (NNs) [36]. NN-based models first gained a tremendous rise in digital image classification due to their superior ability in feature extraction and pattern recognition [37][38][39][40].…”

Section: Introductionmentioning

confidence: 99%

Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review

Liu

Miteva

Delnevo

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Hyperspectral imaging (HSI) has become widely used in cultural heritage (CH). This very efficient method for artwork analysis is connected with the generation of large amounts of spectral data. The effective processing of such heavy spectral datasets remains an active research area. Along with the firmly established statistical and multivariate analysis methods, neural networks (NNs) represent a promising alternative in the field of CH. Over the last five years, the application of NNs for pigment identification and classification based on HSI datasets has drastically expanded due to the flexibility of the types of data they can process, and their superior ability to extract structures contained in the raw spectral data. This review provides an exhaustive analysis of the literature related to NNs applied for HSI data in the CH field. We outline the existing data processing workflows and propose a comprehensive comparison of the applications and limitations of the various input dataset preparation methods and NN architectures. By leveraging NN strategies in CH, the paper contributes to a wider and more systematic application of this novel data analysis method.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review

Liu

Miteva

Delnevo

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

Artomics: A holistic approach to the study of artworks integrating their compositional and formal characteristics. Application on the Liber Feudorum Maior

Magkanas

Bagán

Sistach³

et al. 2023

Microchemical Journal

View full text Add to dashboard Cite

The Role of Formulations in the Ageing Process of Vinyl Acetate Based Emulsion Films: A Multivariate Approach

Viana,

Wieland,

França de Sá

et al. 2024

Polymers

View full text Add to dashboard Cite

Vinyl acetate (VAc)-based emulsions represent one of the main media used by modern and contemporary artists. Their long-term behaviour is still not completely understood, especially due to the scarce knowledge on the influence of other compounds in the formulation, which may impact ageing over time. Besides the polymer backbone based on vinyl acetate, other co-monomers and additives can be added to the emulsion to alter the final film’s physical, chemical, and optical properties. By extension, the formulation will also impact the long-term stability of artworks and objects on which it has been applied, as well as possible current and future conservation interventions such as cleaning. For those reasons, studies shedding light on the correlation between composition and long-term stability are largely necessary. In this study, different emulsions, including homopolymers, copolymers, plasticised, and un-plasticised compositions, were gathered and artificially aged. A multivariate analyses approach based on the application of principal component analyses (PCA) and hierarchical cluster analyses (HCA) was employed for the first time on the combination of data obtained by pH, contact angle (CA), colour measurements, Fourier transform infrared spectroscopy in attenuated total reflection (FTIR-ATR), and size exclusion chromatography (SEC). This approach helped to highlight the changes that occurred during ageing and find correlations with the formulation compositions. The results further sustain the thesis that not all vinyl acetate-based emulsions are chemically the same and that their formulation deeply impacts their long-term behaviour.

show abstract

Hierarchical clustering as an unsurpervised machine learning algorithm for hyperspectral image segmentation of films

Cited by 3 publications

References 13 publications

Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review

Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review

Artomics: A holistic approach to the study of artworks integrating their compositional and formal characteristics. Application on the Liber Feudorum Maior

The Role of Formulations in the Ageing Process of Vinyl Acetate Based Emulsion Films: A Multivariate Approach

Contact Info

Product

Resources

About