Multi-valued and Universal Binary Neurons: Learning Algorithms, Application to Image Processing and Recognition

Multi-valued neurons (MVN) and universal binary neurons (UBN) are neural elements with complex-valued weights and high functionality. It is possible to implement the arbitrary mapping described by partially defined multiple-valued function on the single MVN and the arbitrary mapping described by Boolean function (which may not be threshold) on the single UBN. In this paper we consider some applications carried out using these wonderful features of MVN and UBN. Conception of cellular neural networks based on MVN and UBN becomes a base for nonlinear cellular neural filtering. Application of the corresponding filters for edge detection and solving of the super-resolution problem are considered in the paper.

Multi-valued neurons are the neural processing elements with complex-valued weights, huge functionality (it is possible to implement arbitrary mapping described by partial-defined multiple-valued function on the single neuron), fast converged learning algorithms. Such features of the multi- valued neurons may be used for solution of the different kinds of problems. Special kind of neural network with multi-valued neurons for image recognition will be considered in the paper. Such a network analyzes the spectral coefficients corresponding to low frequencies. A quickly converged learning algorithm and example of face recognition are also presented. The next application of multi-valued neurons proposed in this paper is their using as basic elements of a cellular neural network. Such an approach makes it possible to implement high effective non- linear multi-valued filters. These filters are very effective for reduction of Gaussian, uniform and speckle noise. They are also highly effective for solution of the frequency correction problem. A correction of the high and medium spatial frequencies using multi-valued filters leads to highly effective extraction of details and local contrast enhancement. Two methods for solution of the super- resolution problem using prediction of high frequency coefficients on multi-valued neuron, and correction of the high frequency part of spectrum by multi-valued filtering are proposed also.

This paper is devoted to implementation of the some original image processing algorithms using cellular neural networks on multi-valued and universal binary neurons. High-effective multi-valued filters, their implementation and application to the noise removing and frequencies correction are considered. Algorithms of the edge detection and impulse noise filtering, and their implementation are also considered. Application of the networks from multi-valued neurons to image recognition and to extrapolation of the image orthogonal spectrum to the highest frequencies domain is also presented.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Multi-valued neurons (MVN) are the neural processing elements with complex-valued weights and high functionality. It is possible to implement an arbitrary mapping described by partial-defined multiple-valued function on the single MVN. The MVN-based neural networks are applied to temporal classification of images of gene expression patterns, obtained by confocal scanning microscopy. The classification results confirmed the efficiency of this method for image recognition. It was shown that frequency domain of the representation of images is highly effective for their description.

We consider fast convergence learning algorithms for multi-valued and universal binary neurons. These neurons are suggested to be used for design of neural networks based on CNN paradigm. On the basis of such networks we offer to solve some problems of image processing. For instance, high efficient method for contours detection obtained by learning algorithm described in the paper is presented. Also solution of the XOR-problem on the single neuron is described. >

There are many cases where image processing is performed using the neural network. The content of this Chapter is implementation of CNN (Cellular Neural Network) on a chip in a new original digital approach. First, testing of some features of the proposed cell of the neural network is evaluated. Then the design of the basic circuit containing the cell for the CNN will be introduced. The idea is to use it for a more complex chip with image processing application. CNN have been extensively used in various image processing applications. One of the most important problems in signal processing is noise removal. The input signals mostly arrive from the real world and therefore they contain relatively high amounts of noise. The CNN circuits are capable of removing this noise partly. The possibility of noise removing depends on the template (weight) coefficients between the cells. CNN networks are based on relatively simple principles, very similar to biological neurons. The input signals are multiplied by appropriate weights, the weight matrix being given intuitively, as it is typical for CNN networks. Then they are added and multiplied by the transfer function. We describe also the settings of weights coefficients. CNN have been extensively used in various image processing applications ( Matsumoto & Yokohama, 1990 ) or ( Sziranyi & Csicsvari, 1993 ). The main problem of CNN implementations on a chip is the chip area consumption. The most area is reserved for the multiplexer, so we looked for alternative multiplications. We describe the achieved results with the designed chip. During the creation of the chip architecture we proposed and introduced special original coding for the weight coefficients. After simulations we recognized that the results were better with rounding than without it, but we found that the rounding during multiplication was not as important as we previously expected. Therefore we decided – instead of a hardware multiplexer – to use multiplication realized by simple gate timing of the special signal. The circuit was designed as a digital synchronized circuit. For the design and simulation we used the Xilinx tool. The cell is based on sub-circuits as it will be shown in detail. The Chapter describes the designed circuit. We introduce also our novel simulator for the CNN using the program tool Visual Basic for Application, and its algorithm which was based on the same principle as the planned designed circuit. The network can process the patterns with 400 points of recognition. O pe n A cc es s D at ab as e w w w .ite ch on lin e. co m

Some important ideas of image recognition using neural network based on multi-valued neurons are being developed in this paper. We are going to discuss the recognition of color images, which is reduced to recognition of gray-scale images. An approach, which has been developed, is illustrated by simulation results. Recognition of distortion (blur) types, distortion parameters and recognition of images with distorted training set using the same neural network is also considered. At this time Gaussian blur and motion blur were taken as distortions. This part of work is also illustrated by simulation results.

We describe a novel cellular connectionist neural network model for the implementation of clustering-based Bayesian image segmentation with Gibbs random-field spatial constraints. The success of this algorithm is largely due to the neighborhood constraints modeled by the Gibbs random field. However, the iterative enforcement of the neighborhood constraints involved in the Bayesian estimation would generally require tremendous computational power. Such computational requirement hinders the real-time application of the Bayesian image segmentation algorithms. The cellular connectionist model proposed aims at implementing the Bayesian image segmentation with real-time processing potentials. With a cellular neural network architecture mapped onto the image spatial domain, the powerful Gibbs spatial constraints are realized through the interactions among neurons connected through their spatial cellular layout. This network model is structurally similar to the conventional cellular network. However, in this new cellular model, the processing elements designed within the connectionist network are functionally more versatile to meet the challenging needs of Bayesian image segmentation based on the Gibbs random field. We prove that this cellular neural network does converge to the desired steady state with a properly designed update scheme. Examples of CT volumetric medical image segmentation are presented to demonstrate the potential of this cellular neural network for a specific image segmentation application.

As an important tool to study practical problems of biology, engineering and image processing, the cellular neural networks (CNNs) has caused more and more attention. Some interesting results about the existence of solution for cellular neural networks have been obtained. In this paper, by means of iterative analysis, the existence of periodic solution and the uniform stability of the equilibrium point of impulsive cellular neural networks with distributed delays are considered. Some new results are obtained.

As an important tool to study practical problems of biology, engineering and image processing, the cellular neural networks (CNNs) has caused more and more attention. Some interesting results about the existence for cellular neural networks have been obtained. In this paper, by means of iterative analysis, the existence of periodic solution for Hopfield cellular neural networks are considered. Some new results are obtained.

A new methodology for real-time processing of DNA chip images is proposed. The idea developed here is to use the cellular neural network (CNN) array to analyze the DNA microarray. A CNN is an analog dynamic processor array that reflects this property: the processing elements interact directly within a finite local neighborhood. Due to its architecture, a two-dimensional CNN array is widely used to solve image processing and pattern recognition problems; moreover, the parallelism characteristic of this structure allows one to perform the most computationally expensive image analysis tasks three orders of magnitude faster than a classical CPU-based computer. This approach, thanks to the supercomputing capabilities of the CNN architecture, makes the whole DNA chip methodology fully parallel and also makes the processing phase, until now very time consuming, a real-time step. We discuss the results of testing an algorithm based on the CNN universal machine (CNN-UM) that has been designed to classify the image data. The algorithm is implemented in an analogic (analog and logic) microprocessor.

An implementation method of cellular neural networks (CNN) based on a novel complimentary metal-oxide-semiconductor (CMOS) and single electron transistor (SET) hybrid structure named SETMOS, is proposed in this paper. The main building blocks including cell core circuit, feedback template and control template circuits are designed by the characteristic of negative differential resistance (NDR) of SETMOS and current mirror. Finally, a CNN is constructed and applied in image processing on connected component detector (CCD) and shadow detector (SD). The computer simulation results show that the designed SETMOS CNN circuits, compared to traditional CNN hardware circuits, are suitable for various scale CNN implementation because of simpler structure, lower power dissipation, faster response and higher integrated density. To a certain degree, this kind of designed structure makes it practicability and reliability in image processing.

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, as well as robotic and biological visions. The designs for CNN templates are one of the important i ssues for the practical applications of CNNs. This paper combines two CNN to implement the D ilation CNNs and Erosion CNN for gray scale images and proposes two theorems of robustness designs. The parameters of the templates can range between a hyper plane and a hyper surface in the first quartile. The simulations have been given. The results show the effectiveness of the theoretical results to be implemented in computer simulations. Keywords: Cellular neural network, Robust Design, Dilation, Erosion. 1. INTRODUCTION The CNN was firstly introduced by Chua & Yang [1,2] in 1988. Its original intention is to find out a structure of neural network easier to implement than the Hopfield neural networks[3], which requires fully-connected and grows exponentially with the size of the array. Now CNN has played important roles in many fields such as image and video signal processing, robotic and biological visions, and data prediction[3-8]. In an analog cellular neural network, the parameter levers usually have 5% ý 10% of perturbation [9]. So the robustness designs for CNN template parameters are important for the practical applications of CNN. Chua and Dogaru [3,5] have studied the robust designs of a large kind of CNN-uncoupled Boolean CNNs, which provides optimal design schemes for CNNs with prescribed tasks. Since then, some robust designs for uncoupled and coupled CNNs have been studied (for example see [10-20]), which have been used in image processing and pattern recognitions. Dilation CNN and Erosion CNN for binary image is proposed in Chua and Roska’s book[6]. Then Shu Jian[21] et al. designed the robust of them and proposed two theorems to guarantee the parameters of the templates can perform prescribed dilation or erosion CNN. The pa rameters of templates in [21] will range according the image. In this paper, we separate the original local rules of dilation or erosion CNN into two local rules, then we set up two parameters inequalities of templates to perform each local rules. The parameters of our templates need not range according the image, and parameters values of each template range between one hyper plane and hyper surface. The rest of this paper has organized as follows. Section 2.1 introduces the robust designs of the CNN. Section 2.2 describes and proves two local rules of the Combination C NN which implements the dilati on CNN for gray scale image. Section 2.3 describes and proves two local rules of the Combination CNN which implements erosion CNN for gray scale image. Section 3 gives the examples of the combination CNN. Conclusions have been addressed in Section 4.

The Sixth International Symposium on Neural Networks (ISNN 2009)

As an important tool to study practical problems of biology, engineering and image processing, the cellular neural networks (CNNs) has caused more and more attention.In this paper, by means of iterative analysis, the existence of periodic solution and the uniform stability of the equilibrium point of Hopfield cellular neural networks with impulsive effects are considered.Some new results are obtained.