The paper presents a comparison between hand-crafted and learned descriptors for color texture classification. The comparison is performed on five color texture databases that include images under varying imaging conditions: scales, camera orientations, light orientations, light color temperatures, etc. Results demonstrate that learned descriptors, on average, significantly outperform hand-crafted descriptors. However, results obtained on the individual databases show that in the case of Outex 14, that includes training and test images taken under varying illuminant conditions, hand-crafted descriptors perform better than learned descriptors.

Napoletano, P. (2017). Hand-crafted vs learned descriptors for color texture classification. In Computational Color Imaging. 6th International Workshop, CCIW 2017, Milan, Italy, March 29-31, 2017, Proceedings (pp.259-271). Springer Verlag [10.1007/978-3-319-56010-6_22].

Hand-crafted vs learned descriptors for color texture classification

Napoletano, P
2017

Abstract

The paper presents a comparison between hand-crafted and learned descriptors for color texture classification. The comparison is performed on five color texture databases that include images under varying imaging conditions: scales, camera orientations, light orientations, light color temperatures, etc. Results demonstrate that learned descriptors, on average, significantly outperform hand-crafted descriptors. However, results obtained on the individual databases show that in the case of Outex 14, that includes training and test images taken under varying illuminant conditions, hand-crafted descriptors perform better than learned descriptors.
paper
CNNs; Color texture classification; Global descriptors; Hand-crafted descriptors; Learned descriptors; Local descriptors; Theoretical Computer Science; Computer Science (all)
English
6th International Workshop on Computational Color Imaging, CCIW 2017
2017
Napoletano, P
Bianco, S; Schettini, R; Trémeau, A; Tominaga, S
Computational Color Imaging. 6th International Workshop, CCIW 2017, Milan, Italy, March 29-31, 2017, Proceedings
9783319560090
2017
10213
259
271
http://springerlink.com/content/0302-9743/copyright/2005/
none
Napoletano, P. (2017). Hand-crafted vs learned descriptors for color texture classification. In Computational Color Imaging. 6th International Workshop, CCIW 2017, Milan, Italy, March 29-31, 2017, Proceedings (pp.259-271). Springer Verlag [10.1007/978-3-319-56010-6_22].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/184590
Citazioni
  • Scopus 37
  • ???jsp.display-item.citation.isi??? 34
Social impact