Erratum to: Image processing using cellular neural networks based on multi-valued and universal binary neurons

Journal of Signal Processing Systems -     

Signal processing using cellular neural networks

The cellular neural network (CNN) architecture combines the best features from traditional fully-connected analog neural networks and digital cellular automata. The network can rapidly process continuous-valued (gray-scale) input signals (such as images) and perform many computation functions which traditionally were implemented in digital form. Here, we briefly introduce the the theory of CNN circuits, provide some examples of CNN applications to image processing, and discuss work toward a CNN implementation in custom CMOS VLSI. The role of analog computer-aided design (CAD) will be briefly presented as it relates to analog neural network implementation.This work is supported in part by the Office of Naval Research under Contract N00014-89-J1402, and the National Science Foundation under grant MIP-8912639.     

Image interpolation using neural networks

This work presents an image interpolation method based on a multilayer perceptron. The method is tested in noise-free as well as noisy line doubling and image expansion problems. Two adaptive algorithms are compared. Results show that the proposed method improves image interpolation.     

一种基于量子细胞自动机的三维量子细胞神经网络

以量子细胞自动机为神经元,提出了一种三维的量子细胞神经网络结构;该量子细胞网络包含上下两层的量子细胞自动机阵列,并引入了A模板、B模板以及阈值的概念.以量子细胞自动机的极化率为像素值,通过选择不同的模板、阈值等参数.使得量子细胞神经网络实现了"与"、"或"、"非"操作以及边缘提取等图像处理功能,并利用MATLAB进行了仿真验证,数值仿真结果验证了其在图像处理上的有效性.与传统的细胞神经网络相比,量子细胞神经网络易于实现超大规模且具有超低功耗、超高集成度等优点.     

Image compression using multilayer neural networks

A new neural-network data compression method is presented. The work extends the use of two-layer neural networks to multilayer networks. The results show the performance superiority of multilayer neural networks compared with that of the two-layer one, especially at high compression ratios. To overcome the long training time required for multilayered networks, a previously developed training algorithm has been used. A modified feedback error is proposed to reduce further the training time and to enhance the image quality. Also, a redistribution of the grey levels in the training phase is proposed to make the minimisation of the mean-square error more related to the human-vision system     

Discrete-time cellular neural networks using distributed arithmetic

An efficient digital architecture for the discrete-time cellular neural networks (DTCNNs) is proposed that employs the distributed arithmetic (DA). It consumes little silicon area because of the bit serial computation of DA, and offers higher speed operation than the analogue implementations of DTCNN. The proposed architecture has been implemented in a 0.8 μm CMOS technology     

Experimental identification of universal motor dynamics using neural networks

In this paper a feedforward multilayer Levenberg–Marquardt (LM) neural network-training algorithm is implemented experimentally to identify the weak non-linear dynamics of a universal direct current motor. A flat-spectrum multi-frequency signal is used as the excitation signal. The effects of Gaussian white noise on the identification performance are evaluated quantitatively. The simulation and experimental results confirm that neural network identification is affected by noise, but it is capable to learn, reasonably well, the dynamic pattern of the motor in the presence of noise.     

Nonlinear ultrasonic image processing based on signal-adaptivefilters and self-organizing neural networks

Two approaches for ultrasonic image processing are examined. First, signal-adaptive maximum likelihood (SAML) filters are proposed for ultrasonic speckle removal. It is shown that in the case of displayed ultrasound (US) image data the maximum likelihood (ML) estimator of the original (noiseless) signal closely resembles the L(2) mean which has been proven earlier to be the ML estimator of the original signal in US B-mode data. Thus, the design of signal-adaptive L(2) mean filters is treated for US B-mode data and displayed US image data as well. Secondly, the segmentation of ultrasonic images using self-organizing neural networks (NN) is investigated. A modification of the learning vector quantizer (L(2 ) LVQ) is proposed in such a way that the weight vectors of the output neurons correspond to the L(2) mean instead of the sample arithmetic mean of the input observations. The convergence in the mean and in the mean square of the proposed L(2) LVQ NN are studied. L(2) LVQ is combined with signal-adaptive filtering in order to allow preservation of image edges and details as well as maximum speckle reduction in homogeneous regions.     

Millimeter-wave active imaging using neural networks for signal processing

A neural network has been successfully implemented in an active-mode millimeter-wave (60 GHz) imaging system with a Yagi-Uda antenna array in order to recognize objects and reconstruct images that appear distorted under coherent millimeter-wave illumination. With 10 /spl times/ 10 sampling points and five teaching trials, a recognition rate of 98% has been obtained for ten dissimilar alphabetical letters used as objects. The success rate of reconstruction of distorted millimeter-wave images was 80% when five dissimilar letters were used for the reconstruction. The recognition rate after changing the spatial resolution of the optical system and sampling interval of the image is also discussed.     

Switched-capacitor neural networks using pulse based arithmetic

A possible VLSI implementation of a neural network using SC networks is presented. The frequency of a presynaptic pulse is used as a measure of its state, V/sub j/(f). Synaptic multiplication is made possible by controlling input voltages to the SC multiplier and clock frequencies, V/sub j/(f). Programmable positive and negative weights are allowed. The design is asynchronous and does not require any master clocks.<>     

System identification and modelling based on a double modified multi-valued neural network

A novel identification technique for the extraction of lumped circuit models of general distributed or stray devices is presented. The approach is based on two multi-valued neuron neural networks used in a joined architecture able to extract hidden parameters. The convergence allows the validation of the approximated lumped model and the extraction of the correct values. The inputs of the neural network are the geometrical parameters of a given structure, while the outputs represent the estimation of the lumped circuit parameters. The method uses a frequency response analysis approach in order to elaborate the data to present to the net.     

Radiometric profiling of temperature using algorithm based on neural networks

The retrieval of atmospheric temperature profiles from microwave radiometer brightness temperatures requires the solution of a nonlinear inversion problem. An inversion technique based on neural networks (NN) is developed. The NN technique, compared with the classical inversion methods, exhibits better results in terms of retrieval accuracy, vertical resolution and elaboration time.     

Stability analysis of delayed cellular neural networks described using cloning templates

We show that any N/spl times/M-dimensional delayed cellular neural network described using cloning templates can have no more than 3/sup N/spl times/M/ isolated equilibrium points and 2/sup N/spl times/M/ of these equilibrium points located in saturation regions are locally exponentially stable. In addition, we give the conditions for the equilibrium points to be locally exponentially stable when the equilibrium points locate the designated saturation region. These conditions improve and extend the existing stability results in the literature. The conditions are also very easy to be verified and can be checked by direct examination of the templates, regardless of the number of cells. Finally, the validity and performance of the results are illustrated by use of two numerical examples.     

Equilibrium analysis of cellular neural networks

Cellular neural networks (CNNs) are dynamical systems, described by a large set of coupled nonlinear differential equations. The equilibrium-point analysis is an important step for understanding the global dynamics and for providing design rules. We yield a set of sufficient conditions (and a simple algorithm for checking them) ensuring the existence of at least one stable equilibrium point. Such conditions give rise to simple constraints, that extend the class of CNNs, for which the existence of a stable equilibrium point is rigorously proved. In addition, they are suitable for design and easy to check, because they are directly expressed in term of the template elements.     

基于OpenCV的图像处理

OpenCV是近年来推出的开源、免费的计算机视觉库,利用其所包含的函数可以很方便地实现数字图像和视频处理.同时利用面向对象的VC++6.0编程工具,用C++语言进行程序编写,大大提高了计算机的运行速度.本文首先阐述了OpenCV的特点以及结构,然后以平滑处理、图像形态学为例介绍了OpenCV在数字图像处理中的典型应用....     

Ground states of partially connected binary neural networks

Neural networks defined by outer products of vectors over {-1, 0, 1} are considered. Patterns over {-1, 0, 1} define by their outer products partially connected neural networks consisting of internally strongly connected externally weakly connected subnetworks. Subpatterns over {-1, 1} define subnetworks, and their combinations that agree in the common bits define permissible words. It is shown that the permissible words are locally stable states of the network, provided that each of the subnetworks stores mutually orthogonal subwords, or, at most, two subwords. It is also shown that when each of the subnetworks stores two mutually orthogonal binary subwords at most, the permissible words, defined as the combinations of the subwords (one corresponding to each subnetwork), that agree in their common bits are the unique ground states of the associated energy function     

Stability of cellular neural networks with delay

The problem of stability for cellular neural networks with delay (DCNNs) is studied. A new sufficient condition related to the global asymptotic stability for DCNNs is derived. This condition is less restrictive than that given in the literature     

Nonlinear digital filters mimicking cellular neural networks

This work is motivated by the need forFaithful digital simulation of cellular neural networks (CNNs) that maintains most of their qualitative properties of stability and convergence. An interconnection of nonlinear digital filters mimicking behaviors of the analog CNNs is proposed, and the main properties are studied in detail. The discrete model obtained is proven to have the same convergence properties as the original analog network. The key to this development is the use of anAppropriate discretization scheme. Our discrete approximation to the nonlinear state-space representation of cellular neural networks is such that the Lyapunov function used to show convergence in analog cellular neural networks is still a Lyapunov function (when appropriately discretized) for our nonlinear digital filter network. This is in contrast to other digital simulations of CNNs, which have not been proven to preserve the convergence properties. The network of nonlinear digital filters so introduced thus adds another item to the catalog of digital filters obtained viaappropriate discretization of analog circuits, e.g., wave digital filters, orthogonal filters, and certain other of their more recently studied nonlinear counterparts.All authors were with the Stevens Institute of Technology, Hoboken, NJ, 07670 when this work was performed.Support from NSF grant MIP 9696176.     

No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks

No-reference image quality assessment is of great importance to numerous image processing applications, and various methods have been widely studied with promising results. These methods exploit handcrafted features in the transformation or space domain that are discriminated for image degradations. However, abundant a priori knowledge is required to extract these handcrafted features. The convolutional neural network (CNN) is recently introduced into the no-reference image quality assessment, which integrates feature learning and regression into one optimization process. Therefore, the network structure generates an effective model for estimating image quality. However, the image quality score obtained by the CNN is based on the mean of all of the image patch scores without considering the human visual system, such as edges and contour of images. In this paper, we combine the CNN and the Prewitt magnitude of segmented images and obtain the image quality score using the mean of all the products of the image patch scores and weights based on the result of segmented images. Experimental results on various image distortion types demonstrate that the proposed algorithm achieves good performance.