Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509)

25-25 May 2000

Filter Results

Displaying Results 1 - 25 of 79
  • 2000 6th IEEE International Workshop on Cellular Neural Networks and Their Applications (CNNA 2000) [front matter]

    Publication Year: 2000, Page(s):0_1 - xi
    Request permission for commercial reuse | PDF file iconPDF (354 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2000, Page(s):461 - 462
    Request permission for commercial reuse | PDF file iconPDF (66 KB)
    Freely Available from IEEE
  • CNN with multi-level hysteresis quantization output

    Publication Year: 2000, Page(s):407 - 412
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB)

    This paper presents a novel class of cellular neural networks, where the output is given by the multilevel hysteresis quantization function. Since each cell of elementary CNN has bi-stable piecewise linear function, the image processing is restricted to the black-and-white case. Hence, the architecture provided in this paper would extend availability of CNN. Especially, it is extremely useful for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion segmentation and tracking optimization with edge relaxation in the cellular nonlinear network architecture

    Publication Year: 2000, Page(s):51 - 56
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (336 KB)

    We have developed a high-level set of cellular neural net (CNN) functions for finding the segment-borders of moving objects through spatio-temporal relaxation optimization. They are analogic algorithms based on simple CNN instructions considering their implementability in analogic VLSI chips. Motion information extraction from video series is very power consuming. Most computing effort is devoted ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structure of a CNN cell with linear and second order polynomial feedback terms

    Publication Year: 2000, Page(s):401 - 405
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (176 KB)

    A cellular neural network cell structure that can be used for analyzing brain electrical activity is presented. The cell is fully programmable with both linear and second order polynomial interactions between cells. A multiplier structure is presented in which counteracting nonlinearities are designed to cancel each other out View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The impact of the rule structure on the algorithm of 2D cellular automata implementation

    Publication Year: 2000, Page(s):309 - 314
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    In case of the 2D cellular automata (CA) the whole rule f can be considered the set of sub-junctions grouped due to the number of “ones” in the neighbourhood. Such decomposition enables indication of sub-functions, which are more important for the global dynamics of the automaton then others. The cellular automata can be implemented on a cellular neural network (CNN). The simplest way ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IC design of 8×8 digital CNN with optoelectronic interface

    Publication Year: 2000, Page(s):431 - 436
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (240 KB)

    Presents an optoelectronic CNN system which consists of two integrated circuits connected through flip-chip bonding: a) the photonic GaAs matrix of receivers and emitter; b) the CMOS chip of digital CNN cells with programmable 5-bit weights and threshold currents. This solution is easier to design and is more reliable than analogue circuits. The main advantages of our system include parallel input... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A stored program 2nd order/3-layer complex cell CNN-UM

    Publication Year: 2000, Page(s):213 - 217
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (240 KB)

    A stored program 2nd order/3-layer complex cell cellular neural network Universal Machine (CNN-UM) architecture is introduced. We discuss a number of phenomena that can be generated in this system by a single CNN transient. In particular, it is pointed out that by a proper combination two dynamic layers some operations can be easily implemented that would require an approximation or ite... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modelling of extraction of image fragments in the forms of crosses and rhombuses in the simulated receptive fields

    Publication Year: 2000, Page(s):45 - 49
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    Understanding of possible regimes of animal reactions is based on consideration of possible variants of spatial-temporal dynamic processes of feature extraction from the input stimulus. Detection of crosses and rhombi that have been registered in the neurophysiologic experiments is simulated. The model of one of the functional regimes registered in experiments on animals has been proposed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A cellular neural network stereo vision system for autonomous robot navigation

    Publication Year: 2000, Page(s):117 - 122
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    A complex sensor based control system is presented. The sensor used is a pair of TV cameras providing a stereogram for a stereo vision system based on a cellular neural network. The information thus extracted is used to perform indoor navigation of a robotised platform. Experimental data are provided for a simulated version of the CNN employed. Details of the in progress hardware implementation of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The implementation of a nonlinear wave metric for image analysis and classification on the 64×64 I/O CNN-UM chip

    Publication Year: 2000, Page(s):395 - 400
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB)

    In this paper the implementation of a nonlinear wave metric on the 64×64 I/O CNN-UM chip and its experimental results are presented. The nonlinear wave metric was designed and introduced as a generalized theorem for object analysis and classification. This proposed metric includes the well-known distance measures such as Hamming, Hausdorff metrics as special cases. The defined computational ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The design of cellular neural network with ratio memory for pattern learning and recognition

    Publication Year: 2000, Page(s):301 - 307
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (288 KB)

    In this paper the cellular neural network (CNN) with ratio memory (RM) is implemented in CMOS to recognize and classify the image patterns. In the implemented CMOS CNN, the BJT-based combined four-quadrant multiplier and two-quadrant divider with separated magnitude and sign is used to implement the Hebbien learning function and the ratio memory. Thus, the combined multiplier and divider and the C... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A DTCNN circuit proposal for pixel-level snakes

    Publication Year: 2000, Page(s):425 - 430
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    A VHDL description of a DTCNN circuit for pixel-level snakes is given. This is the first of successive steps in a top-down design flow towards a final physical implementation. The complexity of the application leads us to make use of a multilayer DTCNN with cyclic time variable cloning templates. In order to make a feasible physical implementation, the basic concepts of the CNN Universal Machine (... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A compact digital CNN array for video segmentation system

    Publication Year: 2000, Page(s):229 - 233
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    Ideas are given for implementing a fixed template cellular nonlinear network processor. Our concept is based on calculations in the digital domain so that the desired accuracy can be transformed into selecting appropriate word lengths in different parts of the system. We concentrate on implementing a weighted average circuit that guarantees a true 7 bit accuracy in the processing View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A cellular neural networks approach for non-destructive control of mechanical parts

    Publication Year: 2000, Page(s):159 - 164
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    An approach is proposed using cellular neural networks applied image processing, for the detection and characterisation of superficial faults in mechanical parts. There are above all two advantages deriving from an application of the proposed methodologies: the automization of a procedure, that of non-destructive tests (NDT), which is today carried out manually, and the possibility to reduce to a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A programmable vision chip for CNN based algorithms

    Publication Year: 2000, Page(s):207 - 212
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (228 KB)

    In this paper, an original architecture of cellular neural network (CNN) vision chip is addressed. In the introduction, an analyse of the limitations of the usual approaches leads us to propose an original architecture. The paper is dedicated to the description of the three main blocks of our vision chip. Then, the major building blocks are detailed. Finally, design considerations and the practica... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Straightforward design of robust cellular neural networks for image processing

    Publication Year: 2000, Page(s):39 - 44
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (292 KB)

    The analytical design of cellular neural network (CNN) templates for image processing often goes through the resolution of pixel level analytical rule-based task descriptions involving ideal CNN models. Due to nonideal analog implementations of CNN, recent issues have addressed the template robustness in order to achieve fault-tolerant processing. However, besides their efficiency and usefulness f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hetero-associative memories via globally asymptotically stable discrete-time cellular neural networks

    Publication Year: 2000, Page(s):141 - 145
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (168 KB)

    In this paper hetero-associative memories are designed using globally asymptotically stable discrete-time cellular neural networks (DTCNNs). The approach, which assures the global asymptotic stability of the equilibrium point by exploiting circulant matrices in the design phase, generates networks where the input data are fed via external inputs rather than initial conditions. This feature makes i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal CNN templates for deconvolution

    Publication Year: 2000, Page(s):111 - 116
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    A simplified version of the gradient descent method is introduced as a straightforward way to find optimal 3×3 CNN templates for the inversion of known point spread functions (PSF). In practical applications the determination of this inverse is necessary to fulfil deconvolution tasks. The proposed method is much faster than the previously applied algorithms (like genetic algorithm) and still... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the rectangular grid representation of general CNN networks

    Publication Year: 2000, Page(s):387 - 393
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    Although the cellular neural net (CNN) paradigm in its original form provides a suitable framework for investigating problems defined on arbitrary regular grids, the neural chips available or under design and the available simulators are all restricted to a rectangular structure. It is not at all self-evident, however, that the rectangular structure is the most suitable to represent every practica... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Massively parallel processing implementation of the toroidal neural networks

    Publication Year: 2000, Page(s):295 - 300
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    The toroidal neural networks (TNN), recently introduced, are derived from discrete time cellular neural network (DT-CNN) and are characterized by an appealing mathematical description which allows the development of an exact learning algorithm. In this work, after reviewing the underlying theory, we describe the implementation of TNN on the APE100/Quadrics massively parallel system and, through an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extended SC-CNN implementation of the Hindmarsh-Rose neuron

    Publication Year: 2000, Page(s):339 - 344
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    In this paper an extended state-controlled cellular neural network (SC-CNN) based design of the Hindmarsh-Rose neuron is presented. In particular, both the simplicity and low cost characteristic of the realisation are emphasised. Experimental series of this circuit are examined; either spiking-bursting behaviour or beating activity are observed for different values of a circuit parameter correspon... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamics of a CNN with variable number of couplings

    Publication Year: 2000, Page(s):419 - 424
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (296 KB)

    Dynamics of a CNN in the form of circular chain of coupled bistable active elements is investigated for different number of couplings between elements. It is found that dependences of the boundaries of existence domains for all the considered modes are characterized by a sharp change in the region with the smallest number of couplings View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of a dedicated CNN chip for autonomous robot navigation

    Publication Year: 2000, Page(s):225 - 228
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (244 KB)

    Obstacle avoidance is the main issue in autonomous robotics. It requires a three-dimensional effective environment sensing in real time. Among the others, the stereo vision approach to environmental information extraction seems to be very appealing, even if it leads an extremely high computational cost. However, a high performance implementation of this algorithm on a cellular neural network is ab... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autowaves in noninteger order CNNs

    Publication Year: 2000, Page(s):153 - 158
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    In this paper it is shown that complex spatio-temporal phenomena, usually met in physical and biological systems, can be reproduced by means of cellular neural networks of noninteger order. The template parameters are reported in the paper, together with some simulation results which show the suitability of the approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.