Ella Hendriks

Image processing for artist identification

A survey of the literature reveals that image processing tools aimed at supplementing the art historians toolbox are currently in the earliest stages of development. To jump-start the development of such methods, the Van Gogh and Kroller-Muller museums in The Netherlands agreed to make a data set of 101 high-resolution gray-scale scans of paintings within their collections available to groups of image processing researchers from several different universities. This article describes the approaches to brushwork analysis and artist identification developed by three research groups, within the framework of this data set.

Rhythmic Brushstrokes Distinguish van Gogh from His Contemporaries: Findings via Automated Brushstroke Extraction

Art historians have long observed the highly characteristic brushstroke styles of Vincent van Gogh and have relied on discerning these styles for authenticating and dating his works. In our work, we compared van Gogh with his contemporaries by statistically analyzing a massive set of automatically extracted brushstrokes. A novel extraction method is developed by exploiting an integration of edge detection and clustering-based segmentation. Evidence substantiates that van Goghs brushstrokes are strongly rhythmic. That is, regularly shaped brushstrokes are tightly arranged, creating a repetitive and patterned impression. We also found that the traits that distinguish van Goghs paintings in different time periods of his development are all different from those distinguishing van Gogh from his peers. This study confirms that the combined brushwork features identified as special to van Gogh are consistently held throughout his French periods of production (1886-1890).

Degradation process of lead chromate in paintings by Vincent van Gogh studied by means of spectromicroscopic methods : 3 : synthesis, characterization, and detection of different crystal forms of the chrome yellow pigment

The painter, Vincent van Gogh, and some of his contemporaries frequently made use of the pigment chrome yellow that is known to show a tendency toward darkening. This pigment may correspond to various chemical compounds such as PbCrO(4) and PbCr(1-x)S(x)O(4), that may each be present in various crystallographic forms with different tendencies toward degradation. Investigations by X-ray diffraction (XRD), mid-Fourier Transform infrared (FTIR), and Raman instruments (benchtop and portable) and synchrotron radiation-based micro-XRD and X-ray absorption near edge structure spectroscopy performed on oil-paint models, prepared with in-house synthesized PbCrO(4) and PbCr(1-x)S(x)O(4), permitted us to characterize the spectroscopic features of the various forms. On the basis of these results, an extended study has been carried out on historic paint tubes and on embedded paint microsamples taken from yellow-orange/pale yellow areas of 12 Van Gogh paintings, demonstrating that Van Gogh effectively made use of different chrome yellow types. This conclusion was also confirmed by in situ mid-FTIR investigations on Van Goghs Portrait of Gauguin (Van Gogh Museum, Amsterdam).

Evidence for Degradation of the Chrome Yellows in Van Gogh’s Sunflowers: A Study Using Noninvasive In Situ Methods and Synchrotron‐Radiation‐Based X‐ray Techniques

This paper presents firm evidence for the chemical alteration of chrome yellow pigments in Van Goghs Sunflowers (Van Gogh Museum, Amsterdam). Noninvasive in situ spectroscopic analysis at several spots on the painting, combined with synchrotron-radiation-based X-ray investigations of two microsamples, revealed the presence of different types of chrome yellow used by Van Gogh, including the lightfast PbCrO4 and the sulfur-rich PbCr1-x Sx O4 (x≈0.5) variety that is known for its high propensity to undergo photoinduced reduction. The products of this degradation process, i.e., Cr(III) compounds, were found at the interface between the paint and the varnish. Selected locations of the painting with the highest risk of color modification by chemical deterioration of chrome yellow are identified, thus calling for careful monitoring in the future.

Toward Discovery of the Artist?s Style: Learning to recognize artists by their artworks

Author attribution through the recognition of visual characteristics is a commonly used approach by art experts. By studying a vast number of artworks, art experts acquire the ability to recognize the unique characteristics of artists. In this article, we present an approach that uses the same principles to discover the characteristic features that determine an artists touch. By training a convolutional neural network (PigeoNET) on a large collection of digitized artworks to perform the task of automatic artist attribution, the network is encouraged to discover artist-specific visual features. The trained network is shown to be capable of attributing previously unseen artworks to the actual artists with an accuracy of more than 70%. In addition, the trained network provides fine-grained information about the artist-specific characteristics of spatial regions within the artworks. We demonstrate this ability by means of a single artwork that combines characteristics of two closely collaborating artists. PigeoNET generates a visualization that indicates for each location on the artwork who is the most likely artist to have contributed to the visual characteristics at that location. We conclude that PigeoNET represents a fruitful approach for the future of computer-supported examination of artworks.

Matching canvas weave patterns from processing x-ray images of master paintings

Thread counting algorithms seek to determine from x-ray images the vertical and horizontal thread counts (frequencies) of the canvas weave comprising a paintings support. Our spectral-based algorithm employs a variant of short-time Fourier analysis to the image domain that reveals isolated peaks at the proper vertical and horizontal frequencies. Paintings made on canvas sections cut from the same canvas roll have been hypothesized to have similar, distinctive weave characteristics, allowing art historians to more accurately date paintings. Spatial variation of weave frequency measurements across a painting were cross-correlated using a new measure to determine possible common weave patterns between pairs of x-rays. By analyzing a database of x-rays made from 180 paintings by van Gogh, our algorithms confirmed situations where paintings were known to have been made on canvases cut from the same roll and found new ones.

Algorithms for Old Master painting canvas thread counting from x-rays

The task of determining the weave density in the canvas support of Old Master paintings is introduced as a period extraction problem. Because of the way paintings were commonly prepared and preserved, the threads in the horizontal and vertical directions in the canvas support can be counted from x-ray images of the painting. Current procedures are tedious, time-consuming, and (usually) insufficiently documented. This paper describes the design of an algorithm for counting threads from x-rays that uses the Fourier Transform of the Radon Transform of a portion of the image with some crude, but appropriate, decision-making. The algorithm is presented as a sequence of refinements based on a simple mathematical model of the available image data: high resolution x-rays of paintings by Vincent van Gogh from the collection of the Van Gogh Museum. Over 900 spot counts were performed manually by a student team at Cornell using a graphical user interface created for this project. These manual counts provide a dataset for evaluating performance of the algorithm. A major goal is to convince art historians of the viability of automated (and semi-automated) counting procedures.

On the Utility of Spectral-Maximum-Based Automated Thread Counting from X-Radiographs of Paintings on Canvas

Abstract This paper establishes that the two-dimensional Fourier transform, spectral-maximum-based extraction of thread density appears suited to automatic thread counting from scanned X-radiographs of paintings for a range of European painters from the seventeenth century to the early twentieth century. With regularly woven canvas, striping occurring in color-coded maps of local thread count can be used to identify rollmate candidates originally separated by as much as a few meters, maybe more. These results suggest that recently developed spectral-maximum-based thread counting algorithms are sufficiently sophisticated to support major efforts in archival thread counting as key forensic data in a variety of art historical investigations. Still, the canvas and priming used by some artists require a more refined approach to automated thread counting than a simple spectral-maximum-based scheme.

Reconstructing Van Gogh’s palette to determine the optical characteristics of his paints

The colors of Field with Irises near Arles, painted by Van Gogh in Arles in 1888, have changed considerably. To get an idea of how this painting, as well as other works by Van Gogh, looked shortly after their production, the Revigo (Re-assessing Vincent van Gogh’s colors) research project was initiated. The aim of this project was to digitally visualize the original colors of paintings and drawings by Vincent van Gogh, using scientific methods backed by expert judgement where required. We adopted an experimental art technological approach and physically reconstructed Van Gogh’s full palette of oil paints, closely matching those he used to paint Field with Irises near Arles. Sixteen different paints were reconstructed, among which the most light-sensitive pigments and linseed oil, which is prone to yellowing, were produced according to 19th century practice. The resulting pigments and oils were chemically analyzed and compared to those used by Van Gogh. The ones that resembled his paints the most were used in the paint reconstructions. Other pigments were either obtained from the Cultural Heritage Agency’s collection of historical pigments, or purchased from Kremer Pigmente. The reconstructed paints were subsequently used to calculate the absorption K and scattering S parameters of the individual paints. Using Kubelka–Munk theory, these optical parameters could in turn be used to determine the color of paint mixtures. We applied this method successfully to digitally visualize the original colors of Field with Irises near Arles. Moreover, the set of optical parameters presented here can similarly be applied to calculate digital visualizations of other paintings by Van Gogh and his contemporaries.

Colour Change in Sample - Reconstructions of Vincent van Gogh's Grounds due to Wax-Resin Lining

Abstract This study examined the visual impact (colour change) of wax-resin lining on sample reconstructions of Vincent van Gogs grounds, made as part of the Historically Accurate Oil Painting Reconstruction Techniques (HART) Project. The lining method followed that used by J.C. Traas for lining paintings by Van Gogh between 1926 and 1933. Visual changes in the ground samples after living were noted and colour change was measured using a reflectance spectrophotometer. The binding medium of the ground was found to be the most significant factor, with the greatest darkening occurring in samples bound in glue, followed by emulsion and oil. The presence and the method of application of size used in the preparation of the ground samples and the inorganic composition also influenced darkening and colour change as a result of lining. Grounds on unsized canvas darkened the most, while a layer of gelled size reduced impregnation with the lining adhesive and concomitant darkening. Chalk-containing grounds darkened more than grounds containing barium sulphate or lead white. Comparisons between the reconstruction samples and wax-resin lined paintings by Van Gogh highlighted difficulties in attributing the darkening of the ground in the paintings to the lining or to other factors, such as staining by original oil binder in the paint.