Emerging Information Infrastructures: Cooperation in Disasters
2009 (English)In: Critical Information Infrastructure Security: Third International Workshop, CRITIS 2008, Rome, Italy, October13-15, 2008. Revised Papers / [ed] Roberto Setola, Stefan Geretshuber, Springer Berlin/Heidelberg, 2009, 258-270 p.Conference paper (Refereed)
In this paper we describe how to include high level semantic information, such as aesthetics and emotions; into Content Based Image Retrieval. We present a, color-based emotion-related image descriptor that can be used for describing the emotional content of images. The color emotion metric used is derived from psychophysical experiments rind based oil three variables: activity, weight and teat. It was originally designed for single-colors, bill, recent research has shown that the salve emotion estimates call be applied in the retrieval of multi-colored images. Here we describe a new approach, based oil the assumption that perceived color emotions in images are mainly affected by homogenous regions, defined by the emotion metric; and transitions between regions. RGB coordinates are converted to emotion coordinates, mid for each emotion channel, statistical measurements of gradient magnitudes within a. stack of low-pass filtered images are used for finding interest; points corresponding to homogeneous regions and transitions between regions. Emotion characteristics are derived for patches surrounding cacti interest, point, and saved in a, bag-of-emotions; that for instance, can be used for retrieving images based oil emotional content.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2009. 258-270 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 5508
IdentifiersURN: urn:nbn:se:liu:diva-43670DOI: 10.1007/978-3-642-03552-4_23ISI: 000273604000023Local ID: 74507ISBN: 978-3-642-03551-7ISBN: 978-3-642-03552-4OAI: oai:DiVA.org:liu-43670DiVA: diva2:264530
International Workshop on Critical Information Infrastructures Security, CRITIS, 2008