![](bg8.png)
are very promising, taking into account that the tested
schemes are extremely simple. Only a fraction of
available information, i.e., the line/edge code with-
out amplitude and color information, and without a
linking of scales as explored in the segregation model,
has been used so far. More extensive tests are being
conducted, with more images and objects, concentrat-
ing on a linking of scales and a steering of attention
from coarse to fine scales. Such improved schemes
are expected to yield better results, from very fast de-
tection (where) to slower categorization (where/what)
to recognition (what). The balance between keypoint
and line/edge representations is an important aspect.
ACKNOWLEDGEMENTS
This research is partly financed by PRODEP III Me-
dida 5, Action 5.3, and by the FCT program POSI,
framework QCA III.
REFERENCES
Bar, M. (2003). A cortical mechanism for triggering top-
down facilitation in visual object recognition. J. Cogn.
Neuroscience, (15):600–609.
Bar, M. (2004). Visual objects in context. Nature Reviews:
Neuroscience, 5:619–629.
Berson, D. (2003). Strange vision: ganglion cells as cir-
cadian photoreceptors. TRENDS in Neurosciences,
26(6):314–320.
Deco, G. and Rolls, E. (2004). A neurodynamical cortical
model of visual attention and invariant object recogni-
tion. Vision Res., (44):621–642.
du Buf, J. (1993). Responses of simple cells: events, inter-
ferences, and ambiguities. Biol. Cybern., 68:321–333.
du Buf, J. (1994). Ramp edges, Mach bands, and the func-
tional significance of simple cell assembly. Biol. Cy-
bern., 70:449–461.
du Buf, J. and Fischer, S. (1995). Modeling brightness per-
ception and syntactical image coding. Optical Eng.,
34(7):1900–1911.
Elder, J. and Zucker, S. (1998). Local scale control for
edge detection and blur estimation. IEEE Tr. PAMI,
20(7):699–716.
Fleet, D., Jepson, A., and Jenkin, M. (1991). Phase-based
disparity measurement. CVGIP: Image Understand-
ing, 53(2):198–210.
Grigorescu, C., Petkov, N., and Westenberg, M. (2003).
Contour detection based on nonclassical receptive
field inhibition. IEEE Tr. IP, 12(7):729–739.
Heath, M., Sarkar, S., Sanocki, T., and Bowyer, K. (2000).
A robust visual method for assessing the relative per-
formance of edge-detection algorithms. IEEE Tr.
PAMI, 19(12):1338–1359.
Heitger, F., Rosenthaler, L., von der Heydt, R., Peterhans,
E., and Kubler, O. (1992). Simulation of neural con-
tour mechanisms: from simple to end-stopped cells.
Vision Res., 32(5):963–981.
Hubel, D. (1995). Eye, brain and vision. Scientific Ameri-
can Library.
Hupe, J., James, A., and Bullier, J. (2001). Feedback con-
nections act on the early part of the responses in mon-
key visual cortex. J. Neurophysiol., 85(1):134–144.
Itti, L. and Koch, C. (2001). Computational modeling
of visual attention. Nature Reviews: Neuroscience,
2(3):194–203.
Kr
¨
uger, N. and Peters, G. (1997). Object recognition with
banana wavelets. Proc. 5th Europ. Symp. Artificial
Neural Networks, pages 61–66.
Leibe, B. and Schiele, B. (2003). Analyzing appearance
and contour based methods for object categorization.
Proc. Int. Conf. Comp. Vision Pattern Recogn, Madi-
son (Wisconsin), pages 409–415.
Oliva, A., Torralba, A., Castelhano, M., and Henderson, J.
(2003). Top-down control of visual attention in object
detection. Int. Conf. Im. Proc., 1:253–256.
Pessoa, L. (1996). Mach bands: how many models are pos-
sible? Recent experimental findings and modeling at-
temps. Vision Res., 36:3205–3227.
Rasche, C. (2005). The making of a neuromorphic visual
system. Springer.
Rensink, R. (2000). The dynamic representation of scenes.
Visual Cogn., 7(1-3):17–42.
Riesenhuber, M. and Poggio, T. (2000). Cbf: A new frame-
work for object categorization in cortex. 1st IEEE
Int. Worksh. Biologically Motivated Computer Vision,
Seoul (Korea), pages 1–9.
Rodrigues, J. and du Buf, J. (2004a). Vision frontend with
a new disparity model. Early Cogn. Vision Worksh.,
Isle of Skye (Scotland)
www.cn.stir.ac.uk/ecovision-ws/.
Rodrigues, J. and du Buf, J. (2004b). Visual cortex fron-
tend: integrating lines, edges, keypoints and disparity.
Proc. Int. Conf. Image Anal. Recogn., Springer LNCS
3211(1):664–671.
Rodrigues, J. and du Buf, J. (2005a). Multi-scale cortical
keypoint representation for attention and object detec-
tion. 2nd Iberian Conf. on Patt. Recogn. and Image
Anal., Springer LNCS 3523:255–262.
Rodrigues, J. and du Buf, J. (2005b). Multi-scale keypoints
in V1 and face detection. 1st Int. Symp. Brain, Vi-
sion and Artif. Intell., Naples (Italy), Springer LNCS
3704:205–214.
Smeraldi, F. and Bigun, J. (2002). Retinal vision applied to
facial features detection and face authentication. Pat-
tern Recogn. Letters, 23:463–475.
van Deemter, J. and du Buf, J. (1996). Simultaneous detec-
tion of lines and edges using compound Gabor filters.
Int. J. Patt. Recogn. Artif. Intell., 14(6):757–777.
Zhaoping, L. (2003). V1 mechanisms and some figure-
ground and border effects. J. Physiology, 97:503–515.
VISAPP 2006 - IMAGE UNDERSTANDING
12