Wove Paper Analysis through Texture Similarities

Patrice Abry (1) , Andrew G. Klein (2) , Paul Messier (3) , Stéphane Roux (1) , Margaret Holben Ellis (4) , William A. Sethares (5) , David Picard (6) , Yuanhao Zhai (7) , David L. Neuhoff (7) , Herwig Wendt (8, 9) , Stéphane Jaffard (10) , Richard Johnson (11)

1 Phys-ENS - Laboratoire de Physique de l'ENS Lyon
2 WWU - Western Washington University
3 Yale University [New Haven]
4 NYU - New York University [New York]
5 University of Wisconsin-Madison
6 ENSEA - Ecole Nationale Supérieure de l'Electronique et de ses Applications
7 University of Michigan [Ann Arbor]
8 IRIT-SC - Signal et Communications
9 CNRS - Centre National de la Recherche Scientifique
10 LAMA - Laboratoire d'Analyse et de Mathématiques Appliquées
11 Cornell University [New York]

Wove paper, made on a papermaking screen or mold having a surface of smooth tightly woven wires, was the predominant paper type used for printing in the twentieth century. To aid in the study and classification of fine art prints on wove paper, the present work compares the results of five different image processing approaches for characterizing surface texture. Using a collection of popular wove papers, a reference dataset of raking light close-up images was assembled. Five research teams undertook their own processing strategies to detect affinities among the paper samples. Their success in identifying similarity groupings are reported.

Mots clés: Woven composites; Image classification; Printing; Surface texture

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]; Traitement du signal et de l'image [eess.SP]; Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]

Patrice Abry, Andrew G. Klein, Paul Messier, Stéphane Roux, Margaret Holben Ellis, et al.. Wove Paper Analysis through Texture Similarities. 50th IEEE Annual Asilomar Conference on Signals, Systems, and Computers (ASILOMAR 2016), Nov 2016, Pacific Grove, United States. pp. 144-148. ⟨hal-01726414⟩