An Object Oriented Segmentation on

This paper introduces a real-time object oriented segmentation algorithm, designed and implemented on a new type of mixed analog/digital chip based on the cellular neural/nonlinear network (CNN) paradigm. The fully parallel architecture of the CNN processes all the pixels of an image at the same time, so the time spent for the image segmentation is independent on the number of objects in the image. This implementation of the segmentation algorithm is shown to well satisfy the real-time requirements both as a standing alone processing procedure, and as a module inside the MPEG-4 video coding standard. Finally, the general purpose characteristics of the CNN universal chip allow to use the algorithm introduced as an efficient pre-processing procedure for many interesting image/video standing alone applications. Index Terms—Cellular neural networks (CNNs), object oriented segmentation (OOS), MPEG-4 video coding standard, CNN chip prototype, noise filter.

[1]  P. Arena,et al.  Self-organization in a two-layer CNN , 1998 .

[2]  Leon O. Chua,et al.  Turing patterns in CNNs. I. Once over lightly , 1995 .

[3]  Touradj Ebrahimi,et al.  Dynamic coding of visual information , 1997, IEEE Trans. Circuits Syst. Video Technol..

[4]  Sanjit K. Mitra,et al.  Nonlinear image processing , 2000 .

[5]  Tamás Szirányi,et al.  Object Oriented Motion-Segmentation for Video-Compression in the CNN-UM , 1999, J. VLSI Signal Process..

[6]  István Petrás,et al.  The CADETWin application software design system - a tutorial , 1999 .

[7]  István Petrás,et al.  CNN chip prototyping and development systems , 1999 .

[8]  V.M. Brea,et al.  Image segmentation based on active contours using discrete time cellular neural networks , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[9]  Leon O. Chua,et al.  Several image processing examples by CNN , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[10]  Murat Kunt,et al.  Spatiotemporal Segmentation Based on Region Merging , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Tibor Kozek,et al.  Analogic Macro Code (AMC) : extended Assembly language for CNN computers : version 1.1 , 1998 .

[12]  A. Rodriguez-Vazquez,et al.  A 64/spl times/64 CNN universal chip with analog and digital I/O , 1998, 1998 IEEE International Conference on Electronics, Circuits and Systems. Surfing the Waves of Science and Technology (Cat. No.98EX196).

[13]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[14]  G. Linan,et al.  The CNNUC3: an analog I/O 64x64 CNN universal machine chip prototype with 7-bit analog accuracy , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[15]  Luigi Fortuna,et al.  State Controlled CNN : A New Strategy for Generating High Complex Dynamics (Special Section on Nonlinear Theory and its Applications) , 1996 .

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

[17]  Leon O. Chua,et al.  Analogic CNN algorithms for some image compression and restoration tasks , 1995 .

[18]  Ákos Zarándy,et al.  An analogic CNN engine board with the 64/spl times/64 analog I/O CNN-UM chip , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

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

[20]  John W. Tukey,et al.  Nonlinear (nonsuperposable) methods for smoothing data , 1974 .

[21]  R. Haralick.  Image segmentation survey , 1982 .

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

[23]  Ángel Rodríguez-Vázquez,et al.  ACE16k: A Programmable Focal Plane Vision Processor with 128 x 128 Resolution , 2001 .