Abstract
A biologically plausible theoretical framework to embody cooperative computation in the visual pathway is proposed. From photoreceptors to ganglion cells, visual processing is properly interpreted by means of linear and nonlinear spatio-temporal filters with center-periphery receptive fields and analogic computation.
At cortical level (mainly recurrent pyramidals) hybrid formulations using a combination of local operators (sum plus sigmoid) and conditionals (inferential rules) are more appropriate. This inferential model is quite general, supports analogic and logic computation as particular cases, and should be applicable to bridge the gap between connectionistic and symbolic artificial intelligence in general and between low level and high level vision, in particular.
To illustrate the possibilities of the model, topographic reorganization of connectivity patterns and receptive fields are considered. Adaptive thresholding as a consequence of cooperative consensus on homogeneity measures in the neighbourhood of each neuron has been simulated. Other properties such as self-organization of columns of contrast, orientation, speed or preferred direction can also be modelled as cooperative processes.
Preview
Unable to display preview. Download preview PDF.
References
Lashley, K.S. “In Search of the Engram”. Society of Experimental Biology Symposium n∘ 4: Physiological Mechanisms in Animal Behaviour, University Press, Cambridge, 1950, pp. 454–480.
Luria, A.R., El Cerebro en Acción. Ed. Fontanella. Barcelona, 1974.
Gonzalo, J. Las Funciones Cerebrales Humanas según Nuevos Datos y Bases Fisiológicas. Intituto Cajal de Investigaciones Biológicas, Vol. XLIV. Madrid, 1952.
Delgado, A.E., Modelos Neurocibernéticos de Dinámica Cerebral, Tesis Doctoral, ETSIT, Madrid, 1978.
Mira, J., Delgado, A.E. Zapata, E.L. & Cabello, D. “On the Lesion Tolerance Problem for Co-operative Processes”. In Implementing Finctions: Microprocessors and Firmware. Ed by L. Richter, P. Le Beux, G. Chroust and G. Noguez. pp. 71–80. North-Holland Publishing Company. Amsterdam, 1981.
Gilbert, C.D. & Wiesel, T.N. “Receptive Field Dynamics in Adult Primary Visual Cortex”. Nature, Vol.356, 12 March 1992. pp. 150–152.
Merzenich, M.M., Recanzone, G., Jenkins, W.M., Allard, T.T. & Nudo, R.J. (1988) “Cortical Representational Plasticity”. In P. Rakie & W. Singer, eds. Neurobiology of Neocortex. Wiley.
Mira, J., Delgado, A.E., Alvarez, J.R., de Madrid, A.P. & Santos, M. “Towards More Realistic Self Contained Models of Neurons: High-Order, Recurrence and local learning”. In J. Mira, J. Cabestany and A. Prieto eds. New trends in neural Computation, LNCS 686. Pp. 55–62. Springer Verlag, 1993.
Topkar, V., Kjell, B. and Sood, A. “Object Detection Using Scale-space. In Proceedings of the Applications of Artificial Intelligence VIII Conference, The Int. Society for Optical Engineering, pp. 2–13, Orlando, Fl, April 1990.
Witkin, A.P. “Scale-Space Filtering”. In Proc. of the 8th Joint Conf. on Art.I Imtellige, pp. 1019–1022, Karlsruhe, Germany, 1983.
Paranjape, R.B., Rangayyan, R.N., Morrow, W.M. and Nguyen, H.N. “Adaptive Beighborhood Image Processing”. In Pro. of Visual Communications and Image Processing, Boston, Ma, pages 198–207, SPIE, Bellingham, Wa, 1992.
Haralick, R. M. and Shapiro, L. G. Computer and Robot vision.Addison-Wesley Pub. Comp.
Sahoo, P.K., Soltani, S., Wong, A.K.C. and Chen, Y.C. “Survey of Thresholding Techniques”. Computer Vision, Graphics, and Image Processing, 41(2):233–260, 1988.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mira, J., Manjarrés, A., Ros, S., Delgado, A.E., Alvarez, J.R. (1995). Cooperative organization of connectivity patterns and receptive fields in the visual pathway: application to adaptive tresholding. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_151
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_151
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive