Spatio-temporal CNN algorithm for object segmentation and object recognition

In this paper a spatio-temporal analogic cellular neural network (CNN) algorithm is designed for front-end filtering, segmentation and object recognition. First, a generalized segmentation strategy is presented based on various diffusion models. Both PDE and non-PDE related schemes are discussed and their VLSI complexity is analyzed. In classification (object recognition) a CNN implementation of the autowave metric, a "nonlinear" variant of the Hausdorff metric, is used. This approach turned out to be superior compared to some other classification methods. A number of tests have been completed within the so-called "bubble/debris" segmentation experiments using original and artificial gray-scale images.

[1]  Ángel Rodríguez-Vázquez,et al.  A CNN UNIVERSAL CHIP IN CMOS TECHNOLOGY , 1996 .

[2]  James P. Keener,et al.  Propagation and its failure in coupled systems of discrete excitable cells , 1987 .

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

[4]  Leon O. Chua,et al.  Methods for image processing and pattern formation in Cellular Neural Networks: a tutorial , 1995 .

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

[6]  Tamás Roska,et al.  A fast, complex and efficient test implementation of the CNN Universal Machine , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[7]  Ákos Zarándy,et al.  Implementation of binary and gray-scale mathematical morphology on the CNN universal machine , 1996 .

[8]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Tamás Roska,et al.  CNN-based difference-controlled adaptive non-linear image filters , 1998, Int. J. Circuit Theory Appl..

[10]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[11]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[12]  J. M. Cruz,et al.  A 16 × 16 Cellular Neural Network Universal Chip: The First Complete Single-Chip Dynamic Computer Array with Distributed Memory and with Gray-Scale Input-Output , 1998 .

[13]  Ángel Rodríguez-Vázquez,et al.  A 0.8 micrometer CMOS 2-D Programmable Mixed-Signal Focal-Plane Array Processor with On-Chip Binary Imaging and Instructions Storage , 1997 .

[14]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[15]  S. Espejo,et al.  A CNN universal chip in CMOS technology , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[16]  Tamás Roska,et al.  CNN‐based difference‐controlled adaptive non‐linear image filters , 1998 .

[17]  Ricardo Carmona-Galán,et al.  A CNN Universal Chip in CMOS Technology , 1996, Int. J. Circuit Theory Appl..

[18]  Hermann Haken,et al.  a Wave Approach to Pattern Recognition (with Application to Optical Character Recognition) , 1994 .

[19]  Niklas Nordström.  Biased Anisotropic Diffusion - A Unified Regularization and Diffusion Approach to Edge Detection , 1990, ECCV.

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

[21]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Tamás Roska,et al.  The CNN universal machine , 1993 .