Asymptotic Behavior of Neural Networks and Image Processing

We give in this paper the definition of a formal network and after, some information about the use of its asymptotic properties for segmenting 3D images reconstructed from parallel cross sections (such as those from Computed Tomography or Magnetic Resonance Imaging). The huge size of data makes algorithmic complexity and storage requirements the key points of 3D edge detection. The classical approach consists in computing the gradient by applying an operator which enhances the grey gradient. Most of all these operators are 3D generalization of 2D edge detectors : Roberts[1], Hueckel[2], Prewitt [3], Canny[4],[5],[6], Marr and Hildreth[7],[8] operators. A critical problem of many of these detectors concerns the size of the convolution masks used to implement the operator : small kernel are noise sensitive, but large ones need prohibitive computing times. A solution is to realize an optimal filter with recursive filters [5],[6].

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Didier A. Girard From template matching to optimal approximation by piecewise smooth curves , 1990, Other Conferences.

[3]  Albert Goldbeter,et al.  Theoretical Models for Cell to Cell Signalling , 1991 .

[4]  Mark B. Phillips,et al.  An Algorithm for Locating and Displaying the Intersection of Two Arbitrary Surfaces , 1984, IEEE Computer Graphics and Applications.

[5]  Leonard A. Ferrari,et al.  Curves and Surfaces in Computer Vision and Graphics , 1990 .

[6]  J. Demongeot,et al.  Neural network in the auditory system: Influence of the temporal context on the response represented by a random field , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  R. Bernstein,et al.  Shading 3D-Images from CT Using Gray-Level Gradients , 1986, IEEE Transactions on Medical Imaging.

[8]  J Demongeot,et al.  Random field and neural information. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[9]  S. Lavallee,et al.  A new system for computer assisted neurosurgery , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[10]  M. Basseville,et al.  Détection de contours: méthodes et études comparatives , 1979 .

[11]  P. Lions,et al.  Image selective smoothing and edge detection by nonlinear diffusion. II , 1992 .

[12]  G.-H. Cottet Modèles de réaction-diffusion pour des réseaux de neurones stochastiques et déterministes , 1991 .

[13]  G. Herman,et al.  3D Imaging In Medicine , 1991 .

[14]  P. Laurent Approximation et optimisation , 1972 .

[15]  Philippe Cinquin Application des fonctions-spline au traitement d'images numériques. (On the use of spline fonctions in numerical images processing) , 1987 .

[16]  F. Berthommier Un modèle de la relation entre tonotopie et synchronisation dans le système auditif , 1989 .

[17]  Patrenahalli M. Narendra,et al.  A Separable Median Filter for Image Noise Smoothing , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Henry Fuchs,et al.  Optimal surface reconstruction from planar contours , 1977, CACM.

[19]  A. Babloyantz,et al.  Self-organization, emerging properties, and learning , 1991 .

[20]  A. Chapel,et al.  Imagerie du carpe en trois dimensions. , 1990 .

[21]  Steven W. Zucker,et al.  A Three-Dimensional Edge Operator , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Terry E. Weymouth,et al.  Using Dynamic Programming For Minimizing The Energy Of Active Contours In The Presence Of Hard Constraints , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[23]  Azriel Rosenfeld,et al.  Three-dimensional boundary following , 1989, Comput. Vis. Graph. Image Process..

[24]  Stephane Lavallee,et al.  CHIRURGIE DE LA COLONNE VERTEBRALE ASSISTEE PAR ORDINATEUR : APPLICATION AU VISSAGE PEDICULAIRE , 1990 .

[25]  Azriel Rosenfeld,et al.  Multidimensional Edge Detection by Hypersurface Fitting , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Frédéric Berthommier,et al.  Auditory processing in a post-cochlear neural network vowel spectrum processing based on spike synchrony , 1989, EUROSPEECH.

[27]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[28]  Carl de Boor,et al.  A Practical Guide to Splines , 1978, Applied Mathematical Sciences.

[29]  Jean-Pierre Francoise Systèmes maximaux d'une singularité quasi homogène , 1980 .

[30]  Alvy Ray Smith,et al.  Cellular automata theory , 1969 .

[31]  Rachid Deriche,et al.  3D edge detection using recursive filtering: application to scanner images , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[32]  C T Chen,et al.  Dynamic elastic interpolation for 3D medical image reconstruction from serial cross sections. , 1988, IEEE transactions on medical imaging.

[33]  K. Doi,et al.  Computer-aided detection of microcalcifications in mammograms. Methodology and preliminary clinical study. , 1988, Investigative radiology.

[34]  Jean-Daniel Boissonnat,et al.  Shape reconstruction from planar cross sections , 1988, Comput. Vis. Graph. Image Process..

[35]  René Thom,et al.  Modèles mathématiques de la morphogénèse , 1971 .

[36]  J. Demongeot,et al.  A neural net for processing of stationary signals in the auditory system , 1989 .

[37]  Jacques Demongeot,et al.  Random field and tonotopy: Simulation of an auditory neural network , 1988, Neural Networks.

[38]  Andreas Pommert,et al.  3D-segmentation and display of tomographic imagery , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[39]  Jayaram K. Udupa,et al.  Fast surface tracking in three-dimensional binary images , 1989, Comput. Vis. Graph. Image Process..

[40]  A Goldbeter,et al.  A Model Based on Receptor Desensitization for Cyclic AMP Signaling in Dictyostelium Cells. , 1987, Biophysical journal.

[41]  Jacques Demongeot,et al.  Markovian Spatial Properties of a Random Field Describing a Stochastic Neural Network: Sequential of Parallel Implementation? , 1990, EURASIP Workshop.

[42]  Richard Szeliski,et al.  From splines to fractals , 1989, SIGGRAPH '89.

[43]  Hsun K. Liu,et al.  Two and three dimensional boundary detection , 1977 .

[44]  Laurent D. Cohen,et al.  Building Highly Structured Volume Representations in 3D Medical Images , 1989 .