PHOTOGRAPHIC PAPER TEXTURE CLASSIFICATION USING MODEL DEVIATION OF LOCAL VISUAL DESCRIPTORS

David Picard 1, * Ngoc-Son Vu 1 Inbar Fijalkow 2
* Corresponding author
1 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
2 ICI
ETIS - Equipes Traitement de l'Information et Systèmes
Abstract : This paper investigates the classification of photographic paper tex-tures using visual descriptors. Such classification is called fine grain due to the very low inter-class variability. We propose a novel image representation for photographic paper texture categorization, relying on the incorporation of a powerful local descriptor into an efficient higher-order model deviation where texture is represented by com-puting statistics on the occurrences of specific local visual patterns. We perform an evaluation on two different challenging datasets of photographic paper textures and show such advanced methods in-deed outperforms existing descriptors.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01063123
Contributor : David Picard <>
Submitted on : Saturday, October 11, 2014 - 7:00:04 AM
Last modification on : Thursday, May 3, 2018 - 3:18:06 PM
Long-term archiving on : Monday, January 12, 2015 - 10:06:17 AM

File

1569912353_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01063123, version 1

Collections

Citation

David Picard, Ngoc-Son Vu, Inbar Fijalkow. PHOTOGRAPHIC PAPER TEXTURE CLASSIFICATION USING MODEL DEVIATION OF LOCAL VISUAL DESCRIPTORS. IEEE Int. Conf. on Image Processing, Oct 2014, Paris, France, France. 5 p. ⟨hal-01063123⟩

Share

Metrics

Record views

286

Files downloads

403