High-speed character recognition using a dual cellular neural network architecture (CNND)

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.

An analog Cellular Neural Network (CNN) architecture employing quantum dots to realize various real time image processing applications such as edge and line detections and motion estimation is proposed. In order to obtain programmability to switch between applications, memristive connections between neighboring cells, and for signal amplification and locking resonant tunneling diodes (RTDs) are utilized. Simulations are carried out on a 2D array of the proposed cell structure to demonstrate edge detection and line detection tasks. This work also provides analytical models and simulation results to prove above mentioned real time image processing functionalities.

We present the packet wavelet coder implemented with cellular neural network architecture, and show its superiority over the pyramidal wavelet representation. This paper also demonstrates how the cellular neural universal machine (CNNUM) architecture can be extended to image compression. The packet wavelet coder performs the operation of image compression, aided by CNN architecture. It uses the highly parallel nature of the CNN structure and its speed outperforms traditional digital computers. In packet wavelet coder, an image signal can be analyzed by passing it through an analysis filter banks followed by a decimation process, according to the rules of packet wavelets. The Simulation results indicate that the quality of the reconstructed image is superior by using packet wavelet coding scheme. Finally, a quantization operation is performed in order to translate the coefficient values to discrete environment. Our results are compared with that of pyramidal wavelet representation

Reactors with heavy water coolants and moderators have been used extensively in today's power industry. Monitoring of the moderator condition plays an important role in ensuring normal operation of a power plant. A cellular neural network, the architecture of which has been adapted for hardware implementation, is proposed for use in a system for prediction of the heavy water moderator temperature. A reactor model composed in accordance with the CANDU Darlington heavy water reactor design was used to form the training sample collection and to control correct operation of the neural network structure. The sample components for the adjustment and configuration of the network topology include key parameters that characterize the energy generation process in the core. The paper considers the feasibility of the temperature prediction only for the calandria's central cross-section. To solve this problem, the cellular neural network architecture has been designed, and major parts of the digital computational element and methods for their implementation based on an FPLD have also been developed. The method is described for organizing an optical coupling between individual neural modules within the network, which enables not only the restructuring of the topology in the training process, but also the assignment of priorities for the propagation of the information signals of neurons depending on the activity in a situation analysis at the neural network structure inlet. Asynchronous activation of cells was used based on an oscillating fractal network, the basis for which was a modified ring oscillator. The efficiency of training the proposed architecture using stochastic diffusion search algorithms is evaluated. A comparative analysis of the model behavior and the results of the neural network operation have shown that the use of the neural network approach is effective in safety systems of power plants.

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.

We describe the analog CMOS VLSI implementation of a cellular neural network (CNN) architecture which spatially filters a 2D image by two orientation selective image filters. The image is represented by a set of input currents supplied by an on-chip array of photosensors. The filters are similar to even and odd Gabor filters. The CNN architecture is implemented using two resistive networks coupled by transconductance amplifiers. The tuned orientation can be steered and the filter response scaled by adjusting the conductances of the resistors and gains of the transconductance amplifiers through externally supplied bias voltages. The circuit operation is explained via a variational principle, which defines the filter output as the minimum of a cost function. We report test results from both 25 × 25 and 45 × 45 pixel arrays.

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 practical implementation of a typical CNN algorithm are discussed.

We present the pyramidal wavelet coder implemented with a Cellular Neural Network architecture, as an example of a Cellular Neural Network application, considering that some times it is extremely desired the massive and real-time processing and this kind of architecture fits very well for such purposes. The pyramidal wavelet coder works performing the image wavelet transform plus threshold and quantization operations. The wavelet transform consists essentially in a bank of filters, where an image is passed through them repeatedly, and after each filtering a sampling operation is performed. Once image has been filtered and sampled according the rules of the pyramidal image coder, the threshold operation is carried out, where we pretend to keep only the most significant wavelet coefficients. Finally, a quantization operation is performed in order to translate the coefficient values to a discrete environment.

We present frequency and spatial adaptive packet wavelet coder implemented with cellular neural network architecture. This paper also demonstrates how the cellular neural universal machine (CNNUM) architecture can be extended to image compression. The packet wavelet coder performs the operation of image compression, aided by CNN architecture. It uses the highly parallel nature of the CNN structure and its speed outperforms traditional digital computers. In packet wavelet coder, an image signal can be analyzed by passing it through an analysis filter banks followed by a decimation process, according to the rules of packet wavelets. Traditional packet decomposition adapts to a global frequency distribution, this technique finds the best joint of spatial segmentation and local frequency basis. The simulation results indicate that the quality of the reconstructed image is superior by using frequency and spatial adaptive packet wavelet coding scheme.

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

The paper aims to examine the use of genetic algorithms to optimize subsystems of cellular neural network architectures. The application at hand is character recognition: the aim is to evolve an optimal feature detector in order to aid a conventional classifier network to generalize across different fonts. To this end, a performance function and a genetic encoding for a feature detector are presented. An experiment is described where an optimal feature detector is indeed found by the genetic algorithm. >

The paper discusses the detection of weaknesses and defects on photolithographic masks by cellular neural networks. The detection by cellular neural networks is performed with the advantages of their massive parallel architecture. First a survey is given of actual methods for the detections of weaknesses and defects. Then the relations between the structures of the mask layouts and the real structures of the masks are defined by local design rules. These local design rules can also indirectly be used to detect most weaknesses and defects. After that, the design of the operators for the detection of weaknesses and defects are executed on the basis of the local design rules, using the method of Galias that is practicable by cellular neural networks. Then some examples of weakness and defect detections on real mask images by cellular neural networks are presented. Finally the results and future aims are discussed. >

This paper develops and validates through a series of presentable examples, a comprehensive high-precision, and ultrafast computing concept for solving nonlinear ordinary differential equations (ODEs) and partial differential equations (PDEs) with cellular neural networks (CNN). The core of this concept is a straightforward scheme that we call "nonlinear adaptive optimization (NAOP),” which is used for a precise template calculation for solving nonlinear ODEs and PDEs through CNN processors. One of the key contributions of this work is to demonstrate the possibility of transforming different types of nonlinearities displayed by various classical and well-known nonlinear equations (e.g., van der Pol-, Rayleigh-, Duffing-, Rössler-, Lorenz-, and Jerk-equations, just to name a few) unto first-order CNN elementary cells, and thereby enabling the easy derivation of corresponding CNN templates. Furthermore, in the case of PDE solving, the same concept also allows a mapping unto first-order CNN cells while considering one or even more nonlinear terms of the Taylor's series expansion generally used in the transformation of a PDE in a set of coupled nonlinear ODEs. Therefore, the concept of this paper does significantly contribute to the consolidation of CNN as a universal and ultrafast solver of nonlinear ODEs and/or PDEs. This clearly enables a CNN-based, real-time, ultraprecise, and low-cost computational engineering. As proof of concept, two examples of well-known ODEs are considered namely a second-order linear ODE and a second order nonlinear ODE of the van der Pol type. For each of these ODEs, the corresponding precise CNN templates are derived and are used to deduce the expected solutions. An implementation of the concept developed is possible even on embedded digital platforms (e.g., field programmable gate array (FPGA), digital signal processor (DSP), graphics processing unit (GPU), etc.). This opens a broad range of applications. Ongoing works (as outlook) are using NAOP for deriving precise templates for a selected set of practically interesting ODEs and PDEs equation models such as Lorenz-, Rössler-, Navier Stokes-, Schrödinger-, Maxwell-, etc.

A Cellular Neural Network (CNN) emulator architecture processing real-time video signals is proposed and implemented on FPGA. The main features of this architecture are: 1) No external memory is required; 2) Computation of each pixel is carried out in three clock cycles and; 3) The number of Euler iterations required for the computation of the output values is determined by the number of implemented processor units (PUs). The architecture is based on a single pipelined cell which is employed to emulate a CNN with larger number of neurons. This cell consists of many processing units connected in cascade and working simultaneously. The image data is to be transmitted to the emulator (FPGA) in a progressive manner as in the case of VGA, DVI, progressive cameras or digital interfaced CMOS cameras. The video image pixels are processed and outputted simultaneously with the incoming pixel values. The proposed architecture is realized on a Xilinx Virtex-II FPGA in Celoxica RC203 board and used in an edge detection application. The implemented system is tested to process a 640×480 pixel 60 fps monochrome VGA video input using 18 bit 3×3 CNN templates and the output video is observed on a VGA monitor.

A CAD tool based on SPICE macromodels to simulate simplified faulty, circuit realizations of a fully programmable, two dimensional cellular neural network (CNN) is presented. The models can be easily adapted to match the electrical parameters of real circuit implementations. Generic macromodels for both current mode and voltage mode CNNs are provided. The macromodels not only simulate the conceptual CNN cell, but also provide the capability to model actual CNN architectures and their nonidealities. Moreover, macromodeling provides the capability to determine the effect of parameter variation on the operation of the CNN efficiently without the need for computationally expensive, exhaustive circuit simulations. We have used the CNN macromodels to develop robust testing strategies for detecting faults in VLSI implementations of CNN arrays. Three fault cases are introduced into a CNN array to provide insight to the usefulness of macromodeling. >