Saliency of color image derivatives: a comparison between computational models and human perception

Eduard Vazquez, Theo Gevers, Marcel Lucassen, Joost Van de Weijer, Ramon Baldrich

Research output: Contribution to journalArticleResearchpeer-review

27 Citations (Scopus)

Abstract

In this paper, computational methods are proposed to compute color edge saliency based on the information content of color edges. The computational methods are evaluated on bottom-up saliency in a psychophysical experiment, and on a more complex task of salient object detection in real-world images. The psychophysical experiment demonstrates the relevance of using information theory as a saliency processing model and that the proposed methods are significantly better in predicting color saliency (with a human-method correspondence up to 74.75% and an observer agreement of 86.8%) than state-of-the-art models. Furthermore, results from salient object detection confirm that an early fusion of color and contrast provide accurate performance to compute visual saliency with a hit rate up to 95.2%. © 2010 Optical Society of America.
Original languageEnglish
Pages (from-to)613-621
JournalJournal of the Optical Society of America A: Optics and Image Science, and Vision
Volume27
Issue number3
DOIs
Publication statusPublished - 1 Mar 2010

Fingerprint Dive into the research topics of 'Saliency of color image derivatives: a comparison between computational models and human perception'. Together they form a unique fingerprint.

  • Cite this

    Vazquez, E., Gevers, T., Lucassen, M., Van de Weijer, J., & Baldrich, R. (2010). Saliency of color image derivatives: a comparison between computational models and human perception. Journal of the Optical Society of America A: Optics and Image Science, and Vision, 27(3), 613-621. https://doi.org/10.1364/JOSAA.27.000613