Learning Color Names from Real-World Images - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Learning Color Names from Real-World Images

Joost van de Weijer
  • Function : Author
  • PersonId : 847654
Cordelia Schmid
  • Function : Author
  • PersonId : 831154
Jakob Verbeek


Within a computer vision context color naming is the action of assigning linguistic color labels to image pixels. In general, research on color naming applies the following paradigm: a collection of color chips is labelled with color names within a well-defined experimental setup by multiple test subjects. The collected data set is subsequently used to label RGB values in real-world images with a color name. Apart from the fact that this collection process is time consuming, it is unclear to what extent color naming within a controlled setup is representative for color naming in real-world images. Therefore we propose to learn color names from real-world images. Furthermore, we avoid test subjects by using Google Image to collect a data set. Due to limitations of Google Image this data set contains a sub- stantial quantity of wrongly labelled data. The color names are learned using a PLSA model adapted to this task. Experimental results show that color names learned from real- world images significantly outperform color names learned from labelled color chips on retrieval and classification.
Fichier principal
Vignette du fichier
verbeek07cvpr2.pdf (1.45 Mo) Télécharger le fichier
Vignette du fichier
VSV07.png (316.95 Ko) Télécharger le fichier
VSV07.poster.pdf (1.68 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Other

Dates and versions

inria-00321127 , version 1 (25-01-2011)
inria-00321127 , version 2 (11-04-2011)



Joost van de Weijer, Cordelia Schmid, Jakob Verbeek. Learning Color Names from Real-World Images. CVPR 2007 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-8, ⟨10.1109/CVPR.2007.383218⟩. ⟨inria-00321127v2⟩
476 View
1983 Download



Gmail Facebook X LinkedIn More