Texture classification has a long history in computer vision. In the last decade, the strong affirmation of deep learning techniques in general, and of convolutional neural networks (CNN) in particular, has allowed for a drastic improvement in the accuracy of texture recognition systems. However, their performance may be dampened by the fact that texture images are often characterized by color distributions that are unusual with respect to those seen by the networks during their training. In this paper we will show how suitable color balancing models allow for a significant improvement in the accuracy in recognizing textures for many CNN architectures. The feasibility of our approach is demonstrated by the experimental results obtained on the RawFooT dataset, which includes texture images acquired under several different lighting conditions.

Bianco, S., Cusano, C., Napoletano, P., Schettini, R. (2017). Improving CNN-based texture classification by color balancing. JOURNAL OF IMAGING, 3(3), 1-15 [10.3390/jimaging3030033].

Improving CNN-based texture classification by color balancing

Bianco, S
;
Cusano, C
;
Napoletano, P
;
Schettini, R.
2017

Abstract

Texture classification has a long history in computer vision. In the last decade, the strong affirmation of deep learning techniques in general, and of convolutional neural networks (CNN) in particular, has allowed for a drastic improvement in the accuracy of texture recognition systems. However, their performance may be dampened by the fact that texture images are often characterized by color distributions that are unusual with respect to those seen by the networks during their training. In this paper we will show how suitable color balancing models allow for a significant improvement in the accuracy in recognizing textures for many CNN architectures. The feasibility of our approach is demonstrated by the experimental results obtained on the RawFooT dataset, which includes texture images acquired under several different lighting conditions.
Articolo in rivista - Articolo scientifico
Color balancing; Color characterization; Color constancy; Convolutional neural networks; Deep learning; Texture classification;
convolutional neural networks; color balancing; deep learning; texture classification; color constancy; color characterization
English
2017
3
3
1
15
33
open
Bianco, S., Cusano, C., Napoletano, P., Schettini, R. (2017). Improving CNN-based texture classification by color balancing. JOURNAL OF IMAGING, 3(3), 1-15 [10.3390/jimaging3030033].
File in questo prodotto:
File Dimensione Formato  
10281-179820.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 2.49 MB
Formato Adobe PDF
2.49 MB Adobe PDF Visualizza/Apri

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/10281/179820
Citazioni
  • Scopus 27
  • ???jsp.display-item.citation.isi??? 24
Social impact