Color Emotions for Image Classification and Retrieval
2008 (English)In: Proc. IS&Ts 4th European Conference on Colour in Graphics, Imaging, and Vision, CGIV 2008, 7003 Kilworth Lane, Springfield, VA 22151 USA: Society for Imaging Science and Technology , 2008, , 367-371 p.Conference paper (Refereed)
Many content-based image retrieval systems are not takinginto account high level semantic information. In this paperwe describe our attempts to include color-based emotion-relatedproperties of images in the search. We show that using coloremotion metrics in content-based image retrieval leads to interestingmethods for image retrieval and classification based onsemantic concepts. The color emotion metric used is derivedfrom psychophysical experiments and uses three scales: activity,weight and heat. It was originally designed for single-colorcombinations and later extended to include pairs of colors. Weshow that a modified approach for statistical analysis of coloremotions in images, involving transformations of ordinary RGBhistograms,provides a useful tool for image classification andretrieval. The methods used are both very fast in feature extraction,and descriptor vectors are very short. This is essential inour application where we intend to use it for searching huge imagedatabases containing millions or billions of images.
Place, publisher, year, edition, pages
7003 Kilworth Lane, Springfield, VA 22151 USA: Society for Imaging Science and Technology , 2008. , 367-371 p.
Engineering and Technology Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:liu:diva-42582Local ID: 66301ISBN: 978-0-89208-262-6OAI: oai:DiVA.org:liu-42582DiVA: diva2:263439
Martin Solli and Reiner Lenz, Color Emotions for Image Classification and Retrieval, 2008, Proc. IS&Ts 4th European Conference on Colour in Graphics, Imaging, and Vision, CGIV 2008, 367-371.
Copyright: Society for Imaging Science and Technology (IS&T)