Learning Color Names from Real-World Images

Joost van de Weijer (1) , Cordelia Schmid (1) , Jakob Verbeek (1)

1 LEAR - Learning and recognition in vision

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.

Mots clés: computer vision; image colour analysis; image resolution

Domaines: Apprentissage [cs.LG]

Joost van de Weijer, Cordelia Schmid, Jakob Verbeek. Learning Color Names from Real-World Images. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '07), Jun 2007, Minneapolis, United States. pp.1--8, ⟨10.1109/CVPR.2007.383218⟩. ⟨inria-00321127v1⟩