A Biologically Motivated Scheme for Robust Junction Detection
Junctions provide important cues in various perceptual tasks, such as the determination of occlusion relationship for figureground separation, transparency perception, and object recognition, among others. In computer vision, junctions are used in a number of tasks like point matching for image tracking or correspondence analysis. We propose a biologically motivated approach to junction detection. The core component is a model of V1 based on biological mechanisms of colinear long-range integration and recurrent interaction. The model V1 interactions generate a robust, coherent representation of contours. Junctions are then implicitly characterized by high activity for multiple orientations within a cortical hypercolumn. A local measure of circular variance is used to extract junction points from this distributed representation. We show for a number of generic junction configurations and various artificial and natural images that junctions can be accurately and robustly detected. In a first set of simulations, we compare the detected junctions based on recurrent long-range responses to junction responses as obtained for a purely feedforward model of complex cells. We show that localization accuracy and positive correctness is improved by recurrent long-range interaction. In a second set of simulations, we compare the new scheme with two widely used junction detection schemes in computer vision, based on Gaussian curvature and the structure tensor. Receiver operator characteristic (ROC) analysis is used for a threshold-free evaluation of the different approaches. We show for both artificial and natural images that the new approach performs superior to the standard schemes. Overall we propose that nonlocal interactions as realized by long-range interactions within V1 play an important role for the detection of higher order features such as corners and junctions.
KeywordsReceiver Operator Characteristic Curve Receiver Operator Characteristic Analysis Complex Cell Natural Image Structure Tensor
Unable to display preview. Download preview PDF.
- Adelson, E. H. (200) Lightness perception and lightness illusions. In Gazzaniga, M. S., ed. The New Cognitive Neurosciences, pp. 339–351. MIT Press, Cambridge, MA, 2 edn.Google Scholar
- Beaudet, P.R. (1978) Rotationally invariant image operators. In 4th Int. Joint Conf. on Pattern Recognition, pp. 578–583, Kyoto, Japan.Google Scholar
- Biederman, I. (1985) Human image understanding: recent research and a theory. Computer Vision, Graphics, Image Proc., 32(1):29–73.Google Scholar
- Bosking, W. H., Zhang, Y., Schofield, B., Fitzpatrick, D. (1997) Orientation selectivity and the arrangement of horizontal connections in tree shrew striate cortex. J. Neurosci., 17(6):2112–2127.Google Scholar
- Förstner, W. (1986) A feature based correspondence algorithm for image matching. In Int. Arch. Photogramm. Remote Sensing, volume 26, pp. 176–189.Google Scholar
- Gilbert, C. D. and Wiesel, T. N. (1983) Clustered intrinsic connections in cat visual cortex. J. Neurosci., 3:1116–1133.Google Scholar
- Green, D. M. and Swets, J. A. (1974) Signal Detection Theory and Psychophysics. Krieger, Huntington, NY, 1974.Google Scholar
- Hansen, T. (2002) A neural model of early vision: contrast, contours, corners and surfaces. Doctoral dissertation, Univ. Ulm, Faculty of Computer Science, Dept. of Neural Information Processing. Submitted.Google Scholar
- Hansen, T. and Neumann, H. (1999) A model of V1 visual contrast processing utilizing long-range connections and recurrent interactions. In Proc. 9. Int. Conf. on Artificial Neural Networks (ICANN99), pp. 61–66, Edinburgh, UK.Google Scholar
- Hansen, T. and Neumann, H. (2001) Neural mechanisms for representing surface and contour features. In Stefan Wermter, Jim Austin, and David Willshaw, editors, Emergent Neural Computational Architectures Based on Neuroscience, LNCS/LNAI 2036, pp. 139–153. Springer, Berlin Heidelberg.CrossRefGoogle Scholar
- Harris, C. J. (1987) Determination of ego-motion from matched points. In Proc. Alvey Vision Conference, pp. 189–192, Cambridge, UK.Google Scholar
- Hirsch, J.A. and Gilbert, C.D. (1991) Synaptic physiology of horizontal connections in the cat’s visual cortex. J. Neurosci., 11(6):1800–1809.Google Scholar
- Hubel, D. H. and Wiesel, T. N. (1968) Receptive fields and functional architecture of monkey striate cortex. J. Physiol., 195:215–243.Google Scholar
- Huffman, D. A. (1971) Impossible objects as nonsense sentences. In B. Meltzer and D. Michic, editors, Machine Intelligence 6, pp. 295–323. Edinburgh University Press, Edinburgh.Google Scholar
- Lindeberg, T. (1998) Feature detection with automatic scale selection. Int. J. Comput. Vision, 30(2):77–116.Google Scholar
- McDermott, J.H. (2001) Some experiments on junctions in real images. Master’s thesis, University Colledge London, 2001. Online available from http://persci.mti.edu/∼jmcderm.
- Pasupathy, A. and Connor, C. E. (2001) Shape representation in area V4: positionspecific tuning for boundary conformation. J. Neurophysiol., 86(5):2505–2519.Google Scholar