© The Institution of Engineering and Technology
Visual attention is an indispensable component of complex vision tasks. A multi-scale, complex network-based approach for determining visual saliency is described. It uses degree centrality (conceptually and computationally the simplest among all the centrality measures) over a network of image regions to form a saliency map. The regions used in the network are multiscale in nature with scale selected automatically. Experimental evaluation establishes the superiority of the method over existing saliency methods, even in noisy environments.
References
-
-
1)
-
L. Itti ,
C. Koch
.
Feature combination strategies for saliency-based visual attention systems.
J. Electron. Imag.
,
1 ,
161 -
169
-
2)
-
Schaefer, G., Stich, M.: `UCID – an uncompressed colour image database', Proc. SPIE Storage and Retrieval Methods and Applications for Multimedia, 2004, 5307, p. 472–480.
-
3)
-
Ouerhani, N., Hugli, H.: `Computing visual attention form scene depth', Proc. 15th Int. Conf. on Pattern Recognition, September 2000, 1, p. 375–378.
-
4)
-
T. Kadir ,
M. Brady
.
Saliency, scale and image description.
Int. J. Comput. Vis.
,
2 ,
83 -
105
-
5)
-
Simoncelli, E.P., Freeman, W.T.: `The steerable pyramid: a flexible architecture for multi-scale derivative computation', Proc. IEEE Int. Conf. on Image Processing, 1995, p. III-444–447.
-
6)
-
C. Constantinidis ,
M.A. Steinmetz
.
Posterior parietal cortex automatically encodes the location of salient stimuli.
J. Neurosci.
,
1 ,
233 -
238
-
7)
-
S.M. Pizer ,
D. Eberly ,
D.S. Fritsch
.
Zoom-invariant vision of figural shape: the mathematics of cores.
Comput. Vis. Image Understanding
,
1 ,
55 -
71
-
8)
-
L.W. Renninger ,
J. Coughlan ,
P. Verghese ,
J. Malik
.
An information maximization model of eye movements.
Adv. Neural Inf. Process. Syst.
-
9)
-
Ma, Y.-F., Zhang, H.-J.: `Contrast-based image attention analysis by using fuzzy growing', Proc. 11th ACM Int. Conf. on Multimedia, November 2003, p. 374–381.
-
10)
-
R.A. Young
.
The gaussian derivative model for spatial vision: l. retinal mechanisms.
Spatial Vis.
,
4 ,
273 -
293
-
11)
-
G. Sabidussi
.
The centrality index of a graph.
Psychometrica
,
581 -
603
-
12)
-
T. Sato ,
A. Murthy ,
K.G. Thompson ,
J.D. Schall
.
Search efficiency but not response interference affects visual selection in Frontal eye field.
Neuron
,
583 -
591
-
13)
-
M.Z. Aziz ,
B. Mertsching
.
Fast and robust generation of feature maps for region-based visual attention.
IEEE Trans. Image Process.
,
5 ,
633 -
644
-
14)
-
Hu, Y., Rajan, D., Chia, L.-T.: `Robust subspace analysis for detecting visual attention regions in images', Proc. 13th Ann. ACM Int. Conf. on Multimedia, November 2005, p. 716–724.
-
15)
-
C. Koch ,
S. Ullman
.
Shifts in selective visual attention: towards the underlying neural circuitry.
Human Neurobiology
,
219 -
227
-
16)
-
Hu, Y., Rajan, D., Chia, L.-T.: `Adaptive local context suppression of multiple cues for salient visual attention detection', Proc. IEEE Int. Conf. on Multimedia and Expo., July 2005, p. 346–349.
-
17)
-
Z. Yu ,
H.-S. Wong
.
A rule based technique for extraction of visual attention regions based on real-time clustering.
IEEE Trans. Multimedia
,
4 ,
766 -
784
-
18)
-
J.K. Tsotsos
.
Analyzing vision at the complexity level.
Behav. Brain Sci.
,
423 -
469
-
19)
-
A.M. Treisman ,
G. Gelade
.
A feature-integration theory of attention.
Cogn. Psychol.
,
1 ,
97 -
136
-
20)
-
J. Harel ,
C. Koch ,
P. Perona
.
Graph-based visual saliency.
Adv. Neural Inf. Process. Syst.
-
21)
-
Liu, H., Jiang, S., Huang, Q., Xu, C., Gao, W.: `Region-based visual attention analysis with its application in image browsing on small displays', Proc. 15th Int. Conf. on Multimedia, September 2007, p. 305–308.
-
22)
-
L. Itti ,
P. Baldi
.
Bayesian surprise attracts human attention.
Adv. Neural Inf. Process. Syst.
-
23)
-
Osberger, W., Maeder, A.J.: `Automatic identification of perceptually important regions in an image', Proc. 14th Int. Conf. on Pattern Recognition, August 1998, 1, p. 701–704.
-
24)
-
Hu, Y., Rajan, D., Chia, L.-T.: `Scale adaptive visual attention detection by subspace analysis', Proc. 15th Int. Conf. on Multimedia, September 2007, p. 525–528.
-
25)
-
J.K. Tsotsos ,
S.M. Culhane ,
W.Y.K. Wai ,
Y. Lai ,
N. Davis ,
F. Nuflo
.
Modeling visual attention via selective tuning.
Artif. Intel.
,
507 -
547
-
26)
-
Cheoi, K., Lee, Y.: `Detecting perceptually important regions in an image based on human visual attention characteristic', Proc. Joint IAPR Int. Workshop on Structural, Syntactic, and Statistical Pattern Recognition, 2002, p. 329–338.
-
27)
-
Hou, X., Zhang, L.: `Saliency detection: a spectral residual approach', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, June 2007, p. 1–8.
-
28)
-
M.W. Cannon ,
S.C. Fullenkamp
.
A model for inhibitory lateral interaction effects in perceived contrast.
Vis. Res.
,
8 ,
1115 -
1125
-
29)
-
Greenspan, H., Belongie, S., Goodman, R., Perona, P., Rakshit, S., Anderson, C.H.: `Overcomplete steerable pyramid filters and rotation invariance', Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, June 1994, p. 222–228.
-
30)
-
Kohonen, T.: `A computational model of visual attention', Proc. Int. J. Conf. on Neural Networks, July 2003, 4, p. 3238–3243.
-
31)
-
Courty, N., Marchand, E., Arnaldi, B.: `A new application for saliency maps: synthetic vision of autonomous actors', Proc. Int. Conf. on Image Processing, September 2003, 3, p. III-1065–1068.
-
32)
-
N.D.B. Bruce
.
Features that draw visual attention: an information theoretic perspective.
Neurocomputing
,
125 -
133
-
33)
-
L. Itti ,
C. Koch ,
E. Niebur
.
A model of saliency-based visual attention for rapid scene analysis.
IEEE Trans. Pattern Analysis and Machine Intelligence
,
11 ,
1254 -
1259
-
34)
-
W. Kienzle ,
F.A. Wichmann ,
B. Scholkopf ,
M.O. Franz
.
A non-parametric approach to bottom-up visual saliency.
Adv. Neural Inf. Process. Syst.
-
35)
-
N.D.B. Bruce ,
J.K. Tsotsos
.
Saliency based on information maximization.
Adv. Neural Inf. Process. Syst.
-
36)
-
Begum, M., Mann, G.K.I., Gosine, R.G.: `A biologically inspired bayesian model of visual attention for humanoid robots', Proc. Sixth IEEE-RAS Int. Conf. on Humanoid Robots, December 2006, p. 587–592.
-
37)
-
Maki, A., Nordlund, P., Eklundh, J.-O.: `A computational model of depth-based attention', Proc. 13th Int. Conf. on Pattern Recognition, August 1996, 4, p. 734–739.
-
38)
-
Y. Sun ,
R. Fisher
.
Object-based visual attention for computer vision.
Artifi. Intell.
,
77 -
123
-
39)
-
Stentiford, F.W.M.: `An evolutionary programming approach to the simulation of visual attention', Proc. 2001 Congress on Evolutionary Computation, May 2001, 2, p. 851–858.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2009.0067
Related content
content/journals/10.1049/iet-cvi.2009.0067
pub_keyword,iet_inspecKeyword,pub_concept
6
6