Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs

C Richard Jr Johnson, Paul Messier, William A. Sethares, Andrew G Klein, Christopher Brown, Anh Hoang Do, Philip Klausmeter, Patrice Abry, Stéphane Jaffard, Herwig Wendt, Stephane Roux, Nelly Pustelnik, Nanne van Noord, L.J.P. van der Maaten, E.O. Postma, James Coddington, Lee Ann Daffner, Hanako Murata, Henry Wilhelm, Sally Wood & 1 others Mark Messier

    Research output: Contribution to journalArticleScientificpeer-review

    Abstract

    Surface texture is a critical feature in the manufacture, marketing, and use of photographic paper. Raking light reveals texture through a stark rendering of highlights and shadows. Though close-up raking light images effectively document surface features of photographic paper, the sheer number and diversity of textures used for historic papers prohibits efficient visual classification. This work provides evidence that automatic, computer-based classification of texture documented with raking light is feasible by demonstrating an encouraging degree of success sorting a set of 120 images made from samples of historic silver gelatin paper. Using this dataset, four university teams applied different image-processing strategies for automatic feature extraction and degree of similarity quantification.All four approaches successfully detected strong affinities and outliers built into the dataset. The creation and deployment of the algorithms was carried out by the teams without prior knowledge of the distributions of similarities and outliers.These results indicate that automatic classification of silver gelatin photographic paper based on close-up texture images is feasible and should be pursued. To encourage the development of other classification schemes, the 120-sample “training” dataset used in this work is available to other academic researchers at http://www.PaperTextureID.org.
    Original languageEnglish
    Pages (from-to)159-170
    Number of pages12
    JournalJournal of the American Institute of Conservation
    Volume53
    Issue number3
    Publication statusPublished - 2014

    Fingerprint

    Historic
    Texture
    Close-up
    Outliers
    Gelatin
    Quantification
    Prior Knowledge
    Affinity
    Image Processing
    Marketing
    Feature Extraction
    Rendering

    Cite this

    Johnson, C. R. J., Messier, P., Sethares, W. A., Klein, A. G., Brown, C., Do, A. H., ... Messier, M. (2014). Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs. Journal of the American Institute of Conservation, 53(3), 159-170.
    Johnson, C Richard Jr ; Messier, Paul ; Sethares, William A. ; Klein, Andrew G ; Brown, Christopher ; Do, Anh Hoang ; Klausmeter, Philip ; Abry, Patrice ; Jaffard, Stéphane ; Wendt, Herwig ; Roux, Stephane ; Pustelnik, Nelly ; van Noord, Nanne ; van der Maaten, L.J.P. ; Postma, E.O. ; Coddington, James ; Daffner, Lee Ann ; Murata, Hanako ; Wilhelm, Henry ; Wood, Sally ; Messier, Mark. / Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs. In: Journal of the American Institute of Conservation. 2014 ; Vol. 53, No. 3. pp. 159-170.
    @article{47f16e2f93c244948719bac7336bc5b2,
    title = "Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs",
    abstract = "Surface texture is a critical feature in the manufacture, marketing, and use of photographic paper. Raking light reveals texture through a stark rendering of highlights and shadows. Though close-up raking light images effectively document surface features of photographic paper, the sheer number and diversity of textures used for historic papers prohibits efficient visual classification. This work provides evidence that automatic, computer-based classification of texture documented with raking light is feasible by demonstrating an encouraging degree of success sorting a set of 120 images made from samples of historic silver gelatin paper. Using this dataset, four university teams applied different image-processing strategies for automatic feature extraction and degree of similarity quantification.All four approaches successfully detected strong affinities and outliers built into the dataset. The creation and deployment of the algorithms was carried out by the teams without prior knowledge of the distributions of similarities and outliers.These results indicate that automatic classification of silver gelatin photographic paper based on close-up texture images is feasible and should be pursued. To encourage the development of other classification schemes, the 120-sample “training” dataset used in this work is available to other academic researchers at http://www.PaperTextureID.org.",
    author = "Johnson, {C Richard Jr} and Paul Messier and Sethares, {William A.} and Klein, {Andrew G} and Christopher Brown and Do, {Anh Hoang} and Philip Klausmeter and Patrice Abry and St{\'e}phane Jaffard and Herwig Wendt and Stephane Roux and Nelly Pustelnik and {van Noord}, Nanne and {van der Maaten}, L.J.P. and E.O. Postma and James Coddington and Daffner, {Lee Ann} and Hanako Murata and Henry Wilhelm and Sally Wood and Mark Messier",
    year = "2014",
    language = "English",
    volume = "53",
    pages = "159--170",
    journal = "Journal of the American Institute of Conservation",
    issn = "0197-1360",
    publisher = "Maney Publishing",
    number = "3",

    }

    Johnson, CRJ, Messier, P, Sethares, WA, Klein, AG, Brown, C, Do, AH, Klausmeter, P, Abry, P, Jaffard, S, Wendt, H, Roux, S, Pustelnik, N, van Noord, N, van der Maaten, LJP, Postma, EO, Coddington, J, Daffner, LA, Murata, H, Wilhelm, H, Wood, S & Messier, M 2014, 'Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs', Journal of the American Institute of Conservation, vol. 53, no. 3, pp. 159-170.

    Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs. / Johnson, C Richard Jr; Messier, Paul; Sethares, William A.; Klein, Andrew G; Brown, Christopher; Do, Anh Hoang; Klausmeter, Philip; Abry, Patrice; Jaffard, Stéphane; Wendt, Herwig; Roux, Stephane; Pustelnik, Nelly; van Noord, Nanne; van der Maaten, L.J.P.; Postma, E.O.; Coddington, James; Daffner, Lee Ann; Murata, Hanako; Wilhelm, Henry; Wood, Sally; Messier, Mark.

    In: Journal of the American Institute of Conservation, Vol. 53, No. 3, 2014, p. 159-170.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Pursuing Automated Classification of Historic Photographic Papers from Raking Light Photomicrographs

    AU - Johnson, C Richard Jr

    AU - Messier, Paul

    AU - Sethares, William A.

    AU - Klein, Andrew G

    AU - Brown, Christopher

    AU - Do, Anh Hoang

    AU - Klausmeter, Philip

    AU - Abry, Patrice

    AU - Jaffard, Stéphane

    AU - Wendt, Herwig

    AU - Roux, Stephane

    AU - Pustelnik, Nelly

    AU - van Noord, Nanne

    AU - van der Maaten, L.J.P.

    AU - Postma, E.O.

    AU - Coddington, James

    AU - Daffner, Lee Ann

    AU - Murata, Hanako

    AU - Wilhelm, Henry

    AU - Wood, Sally

    AU - Messier, Mark

    PY - 2014

    Y1 - 2014

    N2 - Surface texture is a critical feature in the manufacture, marketing, and use of photographic paper. Raking light reveals texture through a stark rendering of highlights and shadows. Though close-up raking light images effectively document surface features of photographic paper, the sheer number and diversity of textures used for historic papers prohibits efficient visual classification. This work provides evidence that automatic, computer-based classification of texture documented with raking light is feasible by demonstrating an encouraging degree of success sorting a set of 120 images made from samples of historic silver gelatin paper. Using this dataset, four university teams applied different image-processing strategies for automatic feature extraction and degree of similarity quantification.All four approaches successfully detected strong affinities and outliers built into the dataset. The creation and deployment of the algorithms was carried out by the teams without prior knowledge of the distributions of similarities and outliers.These results indicate that automatic classification of silver gelatin photographic paper based on close-up texture images is feasible and should be pursued. To encourage the development of other classification schemes, the 120-sample “training” dataset used in this work is available to other academic researchers at http://www.PaperTextureID.org.

    AB - Surface texture is a critical feature in the manufacture, marketing, and use of photographic paper. Raking light reveals texture through a stark rendering of highlights and shadows. Though close-up raking light images effectively document surface features of photographic paper, the sheer number and diversity of textures used for historic papers prohibits efficient visual classification. This work provides evidence that automatic, computer-based classification of texture documented with raking light is feasible by demonstrating an encouraging degree of success sorting a set of 120 images made from samples of historic silver gelatin paper. Using this dataset, four university teams applied different image-processing strategies for automatic feature extraction and degree of similarity quantification.All four approaches successfully detected strong affinities and outliers built into the dataset. The creation and deployment of the algorithms was carried out by the teams without prior knowledge of the distributions of similarities and outliers.These results indicate that automatic classification of silver gelatin photographic paper based on close-up texture images is feasible and should be pursued. To encourage the development of other classification schemes, the 120-sample “training” dataset used in this work is available to other academic researchers at http://www.PaperTextureID.org.

    M3 - Article

    VL - 53

    SP - 159

    EP - 170

    JO - Journal of the American Institute of Conservation

    JF - Journal of the American Institute of Conservation

    SN - 0197-1360

    IS - 3

    ER -