Visual saliency from image features with application to compression

P. J. Harding, Neil Robertson

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)
57 Downloads (Pure)


Image feature point algorithms and their associated regional de-
scriptors can be viewed as primitive detectors of visually-salient information.
In this paper, a new method for constructing a visual attention probability
map using features is proposed. (Throughout this work we use SURF features
yet the algorithm is not limited to SURF alone.) This technique is validated
using comprehensive human eye-tracking experiments. We call this algorithm
\Visual Interest" (VI) since the resultant segmentation reveals image regions
that are visually salient during the performance of multiple observer search
tasks. We demonstrate that it works on generic, eye-level photographs and
is not dependent on heuristic tuning. We further show that the descriptor-
matching property of the SURF feature points can be exploited via object
recognition to modulate the context of the attention probability map for a
given object search task, rening the salient area. We fully validate the Visual
Interest algorithm through applying it to salient compression using a pre-blur
of non salient regions prior to JPEG and conducting comprehensive observer
performance tests. When using the object contextualisation, we conclude that
JPEG les are around 33% larger than they need to be to fully represent the
task-relevant information within them. We nally demonstrate the utility of
the segmentation as a Region of Interest in JPEG2000 compression to achieve
superior image quality (measured statistically using PSNR and SSIM) over
the automatically-selected salient image regions while reducing the image le-
size by down to 25% of that of the original. Our technique therefore delivers
superior compression performance through the detection and selective preser-
vation of visually-salient information relevant to multiple observer tasks.
Original languageEnglish
Article number246
Number of pages35
JournalCognitive Computation
Issue number1
Early online date28 Jun 2012
Publication statusPublished - 2012


  • Visual Saliency


Dive into the research topics of 'Visual saliency from image features with application to compression'. Together they form a unique fingerprint.

Cite this