Hyperbolic Wavelet Transform for Historic Photographic Paper Classification ChallengeReportar como inadecuado

Hyperbolic Wavelet Transform for Historic Photographic Paper Classification Challenge - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 ENS Lyon - École normale supérieure - Lyon 2 IRIT - Institut de recherche en informatique de Toulouse 3 LAMA - Laboratoire d-Analyse et de Mathématiques Appliquées 4 LMAM - Laboratoire de Mathématiques et Applications des Mathématiques, EA 3885

Abstract : Photographic paper texture characterization constitutes a challenging image processing task and an important stake both for manufacturers and art museums. The present contribution shows how the Hyperbolic Wavelet Transform, thanks to its joint multiscale and anisotropie nature, permits to achieve an accurate photographic paper texture analysis and characterization. A cepstral-type distance, constructed on the coefficients of the Hyperbolic Wavelet Transform, is then used to measure similarity between pairs of paper textures. Spectral clustering followed by Ascendant Hierarchical Clustering applied to the similarity matrix enables an unsupervised classification of photographic paper sheets. This methodology is applied to a test dataset made available in the framework of the Historic Photographic Paper Classification Challenge. The relevance of the proposed texture characterization and classification procedure is assessed by comparisons against the database documentation provided by experts.

Keywords : Art Wavelet transforms Image processing Photography Cepstral analysis Wavelet analysis

Autor: Stéphane Roux - Patrice Abry - Herwig Wendt - Stéphane Jaffard - Béatrice Vedel -

Fuente: https://hal.archives-ouvertes.fr/


Documentos relacionados