inria-00321127, version 2
Learning Color Names from Real-World Images
Joost Van De Weijer
1Cordelia Schmid
a, 1Jakob Verbeek
a, 1
IEEE Conference on Computer Vision & Pattern Recognition (CPRV '07) (2007) 1--8
Résumé : 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.
- a – INRIA
- 1 : LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- Domaine : Informatique/Apprentissage
- Mots-clés : computer vision – image colour analysis – image resolution
- Versions disponibles : v1 (25-01-2011) v2 (11-04-2011)
- inria-00321127, version 2
- http://hal.inria.fr/inria-00321127
- oai:hal.inria.fr:inria-00321127
- Contributeur : Jakob Verbeek
- Soumis le : Lundi 11 Avril 2011, 11:22:34
- Dernière modification le : Lundi 11 Avril 2011, 11:34:56







Documents associés
Voir aussi
Exporter