CaltechAUTHORS
  A Caltech Library Service

Image Signature: Highlighting Sparse Salient Regions

Hou, Xiaodi and Harel, Jonathan and Koch, Christof (2012) Image Signature: Highlighting Sparse Salient Regions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34 (1). pp. 194-201. ISSN 0162-8828. http://resolver.caltech.edu/CaltechAUTHORS:20120106-112935050

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20120106-112935050

Abstract

We introduce a simple image descriptor referred to as the image signature. We show, within the theoretical framework of sparse signal mixing, that this quantity spatially approximates the foreground of an image. We experimentally investigate whether this approximate foreground overlaps with visually conspicuous image locations by developing a saliency algorithm based on the image signature. This saliency algorithm predicts human fixation points best among competitors on the Bruce and Tsotsos [1] benchmark data set and does so in much shorter running time. In a related experiment, we demonstrate with a change blindness data set that the distance between images induced by the image signature is closer to human perceptual distance than can be achieved using other saliency algorithms, pixel-wise, or GIST [2] descriptor methods.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/TPAMI.2011.146DOIArticle
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5963689PublisherArticle
Additional Information:© 2012 IEEE. Manuscript received 7 Jan. 2011; revised 21 Apr. 2011; accepted 1 June 2011; published online 19 July 2011. The first author would like to thank Anders Hansen, Xiaodong Li, and Emmanuel Candes for their insightful discussions. We gratefully acknowledge Claudia Wilimzig, Amy Chung-Yu Chou, and Tom Laudes, who generated the images and collected data for the change blindness experiment. The research was supported by the NeoVision program at the US Defense Advanced Research Projects Agency (DARPA), by the US Office of Naval Research (via an award made through Johns Hopkins University), by the G. Harold & Leila Y. Mathers Charitable Foundation, and by the WCU (World Class University) program funded by the Ministry of Education, Science and Technology through the National Research Foundation of Korea (R31-10008).
Group:Koch Laboratory, KLAB
Funders:
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA) NeoVision ProgramUNSPECIFIED
Office of Naval Research (ONR)UNSPECIFIED
G. Harold & Leila Y. Mathers Charitable FoundationUNSPECIFIED
National Research Foundation of Korea Ministry of Education, Science and TechnologyR31-10008
Subject Keywords:Saliency; visual attention; change blindness; sign function; sparse signal analysis
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number12359972
Record Number:CaltechAUTHORS:20120106-112935050
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20120106-112935050
Official Citation:Xiaodi Hou; Harel, J.; Koch, C.; , "Image Signature: Highlighting Sparse Salient Regions," Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol.34, no.1, pp.194-201, Jan. 2012 doi: 10.1109/TPAMI.2011.146
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:28698
Collection:CaltechAUTHORS
Deposited By: Jason Perez
Deposited On:09 Jan 2012 19:13
Last Modified:23 Aug 2016 10:08

Repository Staff Only: item control page