Pursuing Automated Classification of Historic Photographic Papers From Raking Light Images

Johnson, Craig; Messier, Paul; Sethares, William A.; Klein, Andrew G.; Brown, Christopher; Hoang, Anh Nguyen; Klausmeyer, Philip; Abry, Patrice; Jaffard, Stéphane; Wendt, Herwig; Roux, Stéphane; Pustelnik, Nelly; Noord, Nanne van; Maaten, Laurens van der; Postma, Eric; Coddington, James; Daffner, Lee Ann; Murata, Hanako; Wilhelm, Henry; Wood, S.L.; Messier, M. D.

doi:10.1179/1945233014y.0000000024

Cited by 27 publications

(27 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is an obvious need to compare the achieved results against those obtained with features both computed on other multiscale representations (e.g., [21]) or based on representations of very different natures (cf. [19] for a first attempt). Devising distances that better match the perceptual, artistic, aesthetic and manufactured nature of photographic paper is a clear next step and an emergent priority.…”

Section: Discussionmentioning

confidence: 99%

“…Inspection of the obtained clusters and comparison with the documentation available for data set 1 leads to the following striking conclusions: ■ All ten samples from a same sheet-and, similarly, all ten samples from a same package-always fall in a common cluster. The median distances between the ten samples from the same sheet and the ten samples from different sheets of the same packet are found to be of the same order of magnitude, indicating a remarkable reproducibility of the manufacturing process [19], [20]. ■ Samples from one given sheet or from one given packet correctly fall within the cluster containing different samples from the same manufacturer and produced to the same specifications of texture and reflectance.…”

Section: Data Set 1: Test Data Setmentioning

confidence: 96%

“…This imaging system, referred to as the TextureScope, has been extensively described in [19] and is shown in Figure 1. It is noncontact and nondestructive and can therefore be easily adapted for use on photographic prints of high intrinsic value.…”

Section: Texture Image Acquisitionmentioning

confidence: 99%

“…The data set and its documentation have been prepared by an expert familiar with the technical and aesthetic history of photographic paper to include both commonly used surfaces and some outliers. Data set 1, further described in [19], is publicly available within the framework of the Historic Photographic Paper Classification Challenge (http://papertextureid.org) developed by Paul Messier and C.R. Johnson.…”

Section: Texture Image Acquisitionmentioning

confidence: 99%

“…■ The classification of the 30 samples representing the diversity of photo papers is found to be clearly driven by both reflectance and texture. The contents of K 7 = l clusters are summarized on the dendrogram in Figure 6(b) (see also [19] and [20]). …”

Section: Data Set 1: Test Data Setmentioning

confidence: 99%

See 4 more Smart Citations

Multiscale Anisotropic Texture Analysis and Classification of Photographic Prints: Art scholarship meets image processing algorithms

Abry

Roux

Wendt

et al. 2015

IEEE Signal Process. Mag.

Self Cite

View full text Add to dashboard Cite

International audienceTexture characterization of photographic prints can provide scholars with valuable information regarding photographers? aesthetic intentions and working practices. Currently, texture assessment is strictly based on the visual acuity of a range of scholars associated with collecting institutions, such as museum curators and conservators. Natural interindividual discrepancies, intraindividual variability, and the large size of collections present a pressing need for computerized and automated solutions for the texture characterization and classification of photographic prints. In the this article, this challenging image processing task is addressed using an anisotropic multiscale representation of texture, the hyperbolic wavelet transform (HWT), from which robust multiscale features are constructed. Cepstral distances aimed at ensuring balanced multiscale contributions are computed between pairs of images. The resulting large-size affinity matrix is then clustered using spectral clustering, followed by a Ward linkage procedure. For proof of concept, these procedures are first applied to a reference data set of historic photographic papers that combine several levels of similarity and second to a large data set of culturally valuable photographic prints held by the Museum of Modern Art in New York. The characterization and clustering results are interpreted in collaboration with art scholars with an aim toward developing new modes of art historical research and humanities-based collaboration

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data Set 1: Test Data Setmentioning

confidence: 96%

Section: Texture Image Acquisitionmentioning

confidence: 99%

Section: Texture Image Acquisitionmentioning

confidence: 99%

Section: Data Set 1: Test Data Setmentioning

confidence: 99%

See 3 more Smart Citations

Multiscale Anisotropic Texture Analysis and Classification of Photographic Prints: Art scholarship meets image processing algorithms

Abry

Roux

Wendt

et al. 2015

IEEE Signal Process. Mag.

Self Cite

View full text Add to dashboard Cite

show abstract

A Review of Univariate and Multivariate Multifractal Analysis Illustrated by the Analysis of Marathon Runners Physiological Data

Jaffard,

Saës,

Nasr

et al. 2023

Trends in Mathematics

View full text Add to dashboard Cite

Anisotropy of Hölder Gaussian random fields: characterization, estimation, and application to image textures

Richard

2017

Stat Comput

View full text Add to dashboard Cite

The characterization and estimation of the Hölder regularity of random elds has long been an important topic of Probability theory and Statistics. This notion of regularity has also been widely used in Image Analysis to measure the roughness of textures. However, such a measure is rarely sucient to characterize textures as it does not account for their directional properties (e.g. isotropy and anisotropy). In this paper, we present an approach to further characterize directional properties associated to the Hölder regularity of random elds. Using the spectral density, we dene a notion of asymptotic topothesy which quanties directional contributions of eld high-frequencies to the Hölder regularity. This notion is related to the topothesy function of the so-called anisotropic fractional Brownian elds, but is dened in a more generic framework of intrinsic random elds. We then propose a method based on multi-oriented quadratic variations to estimate this asymptotic topothesy. Eventually, we evaluate this method on synthetic data and apply it for the characterization of historical photographic papers.

show abstract

Pursuing Automated Classification of Historic Photographic Papers From Raking Light Images

Cited by 27 publications

References 8 publications

Multiscale Anisotropic Texture Analysis and Classification of Photographic Prints: Art scholarship meets image processing algorithms

Multiscale Anisotropic Texture Analysis and Classification of Photographic Prints: Art scholarship meets image processing algorithms

A Review of Univariate and Multivariate Multifractal Analysis Illustrated by the Analysis of Marathon Runners Physiological Data

Anisotropy of Hölder Gaussian random fields: characterization, estimation, and application to image textures

Contact Info

Product

Resources

About