Abstract
Perception is a major problem which is studied as well in life science as in engineering science: This paper concerns a reflection about some of the early mechanisms which underlie perception. Examples are taken in the field of vision in biology and in computer vision, showing the necessity of some adequate pre-processing of the signals. Then, perception appears as a process of representation of signals, that is, as a process of data analysis aimed at finding the structure of the data. Two examples of artificial neural networks are presented to illustrate the problem of data representation. The first one called “Independent Component Analysis” is close to the signal level, the second one, called “Curvilinear Component Analysis” can be seen as a smooth transition between the aspects of Signal Processing and those of Data Analysis.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Adiv G., (1985) Determining 3-D Motion and Structure from Optical flow generated by Several Moving Objects. IEEE Trans. PAMI, vol. 7, N∘ 4.
Atick J., (1992) What does the Retina Know about Natural Scenes. Neural Computation, 4, 196–210.
Beaudot W, Palagi P, Hérault J., (1993) Realistic Simulation Tool for Early Visual Processing including Space, Time and Colour Data. International Workshop on Artificial Neural Networks IWANN'93, Barcelona, Spain
Cappellini V., Mecocci A., (1993) Motion Analysis and Representation in Computer Vision. Journal of Circuits, Systems and Computers, Vol. 3, N∘ 4.
Demartines P. (1994) Analyse de données par réseaux de neurones auto-organisés. Thèse de Doctorat de l'Institut National Polytechnique de Grenoble, 26 Nov. 1994.
Demartines P., Hérault J., (1993) Representation of non-linear data structures through fast VQP neural networks. Proceedings of Neuro-Nîmes'93, Nîmes (France).
Droulez J., Darlot C., (1989) The geometric and dynamic implications of the coherent constraints in three-dimensional sensorimotor interactions. Attention and Performance, 14, 4105–526.
Franceschini N., Pichon J. M., Blanes C. (1992) From insect vision to robot vision. Phil. Trans. Roy. Soc. London. B 337, 283–294.
Gersho A., Gray R. M. (1992) Vector quantization and signal compression. Kluwer Academic Publishers, London.
Hérault J., Jutten C. (1994) Réseaux neuronaux et traitement du signal. Traité des nouvelles technologies, Hermes, Paris.
Jutten C., Hérault J., (1991) Blind separation of sources. Part I: an adaptive algorithm based on a neuromimetic architecture. Signal Processing, Vol. 24, 1–10.
Kohonen T., (1984) Self-organisation of topologically correct feature maps. Biological cybernetics, 43, 59–69.
Liu X., Hérault J., (1991) Colour image processing by a neural network model. International Neural Network Conference INNC'91, July 9–13, Paris (France).
Livingstone M., Hubel D. H., (1988) Segregation of form, colour, movement and depth: anatomy, physiology and perception. Science, 240, 740–749.
Marr D., (1982) Vision: a computational investigation into the human representation and processing of visual information. WH Freeman & Co, San Francisco
Nguyen Thi H. L., Jutten C., (1995) Blind source separation for convolutive mixtures. Signal Processing, (to appear).
Pettet M. W., Gilbert C. D., (1992) Dynamic changes in receptive-field size in cat primary visual cortex. Proceedings of National Academy of Science, USA, Vol. 89; 8366–8370.
Sammon W. J., (1969) A non-linear mapping algorithm for data structure analysis. IEEE Trans. on Computers, Vol. C-18, N∘ 5, 401–409.
Schölkopf B., Mallot H. P., (1994) View-based cognitive mapping and path planning. Technical report N∘ 7, Max Plank Institut für biologische Kybernetik, Tübingen, Germany.
Shepard R. N., Carrol J. D., (1965) Parametric representation of non-linear data structures. In International Symposium on Multivariate Analysis, Krishnaiah P. R, editor, Academic Press.
Sull S., Ahuja N., (1994) Integrated 3-D Analysis-Guided Synthesis of Flight Image Sequences. IEEE Trans. PAMI, Vol. 16, N∘ 4.
Sune J. L., Puget P., Samy R., (1993) Computation of the depth-from-motion problem from neural networks. Proceedings of Neuro-Nîmes'93, NÎMES (France).
Tononi G., Sporns O., Edelman G. M., (1992) Reentry and the problem of integrating multiple cortical areas: Simulation of dynamic integration in the visual system. Cerebral Cortex, Vol. 2, N∘ 4, 316–335.
Treisman A., (1988) Features and objects: the fourteenth Barlett Memorial Lecture. Quarterly Journal of Experimental Psychology, Vol. 40 A, 201–237.
Walter J. A, Schulten K. J., (1993) Implementation of Self-Organising Neural Networks for Visuo-Motor Control of an Industrial Robot. IEEE Trans. on Neural Networks, Vol. 4, N∘ 1.
Zupan L., (1995) Modélisation du réflexe vestibulo-occulaire et prédiction des cinétoses. Thèse de Doctorat, École Nationale Supérieure des Télécommunications, Paris (France).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hérault, J. (1995). About some perception problems in neural networks. 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_259
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_259
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