By Topic

2005 9th International Workshop on Cellular Neural Networks and Their Applications

Date 28-30 May 2005

Filter Results

Displaying Results 1 - 25 of 87
  • [Cover]

    Publication Year: 2005, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (887 KB)
    Freely Available from IEEE
  • Proceedings. 9th IEEE International Workshop on Cellular Neural Networks and their Applications (IEEE Cat. No. 05TH8814)

    Publication Year: 2005
    Request permission for commercial reuse | PDF file iconPDF (1767 KB)
    Freely Available from IEEE
  • Copyright page

    Publication Year: 2005, Page(s): nil2
    Request permission for commercial reuse | PDF file iconPDF (45 KB)
    Freely Available from IEEE
  • Preface

    Publication Year: 2005, Page(s):nil4 - nil5
    Request permission for commercial reuse | PDF file iconPDF (229 KB) | HTML iconHTML
    Freely Available from IEEE
  • Conference committee

    Publication Year: 2005, Page(s):nil6 - nil9
    Request permission for commercial reuse | PDF file iconPDF (159 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2005, Page(s):i - v
    Request permission for commercial reuse | PDF file iconPDF (498 KB)
    Freely Available from IEEE
  • Image segmentation based on consensus voting

    Publication Year: 2005, Page(s):1 - 4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2376 KB) | HTML iconHTML

    This paper presents a new approach called consensus voting neural network (CVNN) which aims to perform fast image segmentation for grey images. A learning algorithm based on the principle of vote-to-consensus is developed to train CVNN. The essence of CVNN is the iterative interaction between the target neuron and its neighboring pixels, and the range of neighborhood is defined by the running mask... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formation and variability of orientation preference maps in visual cortex: an approach based on normalized Gaussian arrays

    Publication Year: 2005, Page(s):5 - 8
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1336 KB) | HTML iconHTML

    This work explores formation and variability of orientation preference maps in visual cortex based on normalized Gaussian arrays. An orientation preference map, which has been measured to sketch the orientation preference of neighboring neurons in visual cortex, is emulated by a network of weighted normalized Gaussian arrays. Here the orientation preference map is represented by a set of paired da... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel dynamic structural neural network with neuro-regeneration and neuro-degeneration

    Publication Year: 2005, Page(s):9 - 14
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4000 KB) | HTML iconHTML

    This paper presents a novel dynamic structural neural network (DSNN) and a learning algorithm for training DSNN. The performance of a neural network system depends on several factors. In that, the architecture of a neural network plays an important role. The objective of the developing DSNN is to avoid trial-and-error process for designing a neural network system. The architecture of DSNN consists... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of chaotic system using recurrent compensatory neuro-fuzzy systems

    Publication Year: 2005, Page(s):15 - 18
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB) | HTML iconHTML

    In this paper, a recurrent compensatory neuro-fuzzy system (RCNFS) is proposed for identification and prediction. The compensatory-based fuzzy reasoning method is using adaptive fuzzy operations of neuro-fuzzy systems that can make the fuzzy logic systems more adaptive and effective. The recurrent network is embedded in the RCNFS by adding feedback connections in the second layer, where the feedba... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The application of conductivity on the electronic tongue

    Publication Year: 2005, Page(s):19 - 22
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2504 KB) | HTML iconHTML

    Research finds there are five basic tastes in liquid that can be recognized by human tongue. In general, the electronic tongue is an instrument that mimics human tongue to recognize the tastes in liquid. The proposed electronic tongue system includes three subsystems, i.e., chemical sensors array, analog front end, and data treatment and taste comparison subsystem. The electrolytic conductivity si... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified in-cell ADC using ranked order extraction

    Publication Year: 2005, Page(s):23 - 26
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (784 KB) | HTML iconHTML

    For adopting a mixed-mode approach for an array processor implementation, the reuse of analog components is one of the main motivations. This paper describes a modification of a previously presented ADC, in which the two most significant bits of the conversion are generated with the help of a ranked order filter and some additional logic. This strategy saves area in the ADC by efficient reuse of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dedicated hardware for parallel extraction of local binary pattern feature vectors

    Publication Year: 2005, Page(s):27 - 30
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1792 KB) | HTML iconHTML

    In this paper we propose a dedicated hardware for extraction of local binary pattern (LBP) feature vectors. The LBP method transforms local features of image data into binary micro-patterns that represent local and global features of the image. The LBP method can be used in applications such as texture classification, moving object detection and face detection and recognition. The hardware propose... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Realization of neural network controller for electromotor frequency conversion speed-regulating based on LonWorks

    Publication Year: 2005, Page(s):31 - 35
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (896 KB) | HTML iconHTML

    In this paper, we present a study of neural network controller-based solution for electromotor frequency conversion speed-regulating. The neural network controller combines neural network model - M-P(McCulloch-Pitts) with motor speed closed-loop control. The LonWorks technology offers engineers a powerful solution for realization DCS (distributed control system) monitoring and control system. So, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 1-V CMOS similarity measurement chip for binary pattern identification

    Publication Year: 2005, Page(s):36 - 39
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2528 KB) | HTML iconHTML

    The design of a new low-voltage similarity measurement circuit is proposed in this paper. The similarity measurement between two binary patterns is represented by Hamming metric, that is, average absolute differential function. Using clock bootstrapped and level shift techniques, the supply voltage of the circuit is reduced to 1 V, which can efficiently operate within a battery supply. Some simple... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The real-time image processing based on DSP

    Publication Year: 2005, Page(s):40 - 43
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB) | HTML iconHTML

    At present, wavelet transform is gradually used in the processing of video and image. But the algorithm of 2D wavelet transform is too burdensome and complicated to process huge amount of image data in real-time. To the problem, this paper proposes a novel method to process video and image real-timely based on DSP. At the aspect of wavelet algorithm, the method changes the traditional image convol... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A memory-efficient pipeline architecture for 2-D DWT of the 9/7 filter for JPEG 2000

    Publication Year: 2005, Page(s):44 - 47
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3408 KB) | HTML iconHTML

    In this paper, we propose a memory-efficient pipeline architecture which performs the one-level two-dimensional discrete wavelet transform (2D DWT) of the 9/7 filter for JPEG 2000. In general, the internal memory size of 2D architecture highly depends on the pipeline registers of 1D DWT. Based on the lifting-based DWT algorithm, the primitive data path is modified. Thus, an efficient pipeline arch... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust stability of uncertain cellular neural network for image processing - an LMI approach

    Publication Year: 2005, Page(s):48 - 51
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB) | HTML iconHTML

    In this paper, a network called a discrete-time cellular neural network (DTCNN) with uncertainty is introduced. A methodology for the robust stability of the DTCNN is presented. The uncertainties are assumed to be norm-bounded. The methodology is based on the Lyapunov functional combining with linear matrix inequality (LMI) approach. An example is provided to illustrate the effectiveness of the pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel architecture for converting single 2D image into 3D effect image

    Publication Year: 2005, Page(s):52 - 55
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1984 KB) | HTML iconHTML

    A novel 2D to 3D effect image conversion architecture integrated image segmentation system and depth estimation is presented. Its objective is to describe the technique used to generate stereo pair images starting from a single image source (a view-point) and its related depth map. The conjunction between segmented image and depth map allows reconstructing artificially the binocular view producing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bioinformatics advances in neuron imaging

    Publication Year: 2005
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (192 KB) | HTML iconHTML

    Exploring the role of neuron's morphological change in brain function or neurological disorders is a long-time goal in many neuroscience fields. The arrival of digital microscopy, such as two-photon and confocal laser scanning microscopy, coupled with a large arsenal of fluorescent and other labeling methods to study the neuron 3D structure and dynamics in cell culture, brain tissue culture, and e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pattern recognition using finite-iteration cellular systems

    Publication Year: 2005, Page(s):57 - 60
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2912 KB) | HTML iconHTML

    Cellular systems are defined by cells that have an internal state and local interactions between cells that govern the dynamics of the system. We propose to use a special kind of cellular neural networks (CNNs) which operates in finite iteration discrete-time mode and mimics the processing of visual perception in biological systems for digit recognition. We propose also a solution to another type ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CNN-based automatic retinal vascular tree extraction

    Publication Year: 2005, Page(s):61 - 64
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5072 KB) | HTML iconHTML

    The retinal vascular tree has become an important task of medical image processing in different scientific areas. Many studies have focused on developing an automatic algorithm, however little attention has been paid to improve computational processing time of these algorithms. In this paper, an automatic methodology for retinal vascular tree extraction using cellular neural networks (CNNs) is pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CNN-based object recognition with deformable grids and multiple-feature image representation

    Publication Year: 2005, Page(s):65 - 68
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1848 KB) | HTML iconHTML

    The following paper presents a new direction that opens for deformable grid-based object recognition methods, due to introduction of their efficient, parallel implementations. A substantial increase in object recognition performance can be expected when several different features are used to build a class prototype. This would imply extending complexity of image analysis, through an application of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Open-close by reconstruction on CNNUM

    Publication Year: 2005, Page(s):69 - 72
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2824 KB) | HTML iconHTML

    Open-close by reconstruction is one of the most important algorithms in mathematical morphology. It is used widely in image and video processing, but it requires the huge computational power, what is the bottleneck for application. So in this paper, cellular neural network (CNN) is used to solve the problem, new +1 template and "and" template are designed here. Along with the already developed tem... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural mesh on cellular neural network

    Publication Year: 2005, Page(s):73 - 76
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1560 KB) | HTML iconHTML

    This paper presents an implementation of the neural mesh on the cellular neural networks (CNN). An energy function is devised for the mesh to cope with the CNN. This energy can guide various behaviors of the mesh. View full abstract»

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