Watermarking on CNN‐UM for image and video authentication

In this paper a new approach to fragile watermarking technique is introduced. This problem is particularly interesting in the field of modern multimedia applications, when image and video authentication are required. The approach exploits the cellular automata suitability to work as pseudorandom pattern generators and extends the related algorithms under the framework of the cellular non‐linear networks (CNNs). The result is a novel way to perform watermarking generation in real time, using the presently available CNN‐universal chip prototypes. In this paper, both the CNN algorithms for fragile watermarking as well as on‐chip experimental results are reported, confirming the suitability of CNNs to successfully act as real‐time watermarking generators. The availability of CNN‐based visual microprocessors allows to have powerful algorithms to watermark in real time images or videos for efficient smart camera applications. Copyright © 2004 John Wiley & Sons, Ltd.     

Spatial logic algorithms using basic morphological analogic CNN operations

The CNN implementation of basic scale-, rotation- and translation-invariant morphological functions and novel types of analogic CNN algorithms using spatial logic are introduced for object recognition (detection) purposes. The power of the technique is illustrated on bank-note recognition tasks.     

SPATIAL DEPTH EXTRACTION USING RANDOM STEREOGRAMS IN ANALOGIC CNN FRAMEWORK

Demonstrated and motivated on human stereo vision analogic CNN algorithms are proposed to extract 3D spatial information from computer-generated random-dot stereograms as well as real scene random-dot like ones produced with simple optical devices, projector and camera. Several aspects of making real scene stereograms are considered to minimize perspective distortion and enable local CNN processing.     

The analogic cellular neural network as a bionic eye

The conception of the CNN universal machine has led quite naturally to the invention of the analogic CNN bionic eye (henceforth referred to simply as the bionic eye). the basic idea is to combine the elementary functions, the building blocks, of the retina and other 2 1/2 D sensory organs, algorithmically, in a stored programme of a CNN universal machine, through the use of artificial analogic programmes. the term bionic is defined in a rigorous way: it is a nonlinear, dynamic, spatiotemporal biological model implemented in a stored programme electronic (optoelectronic) device; this device is in our case the analogic CNN universal machine (or chip). The aim of this paper is to report on this new invention, particularly to electronic and computer engineers, in a tutorial way. We begin by summarizing (1) the biological aspects of the range of retinal function (the retinal universe), (2) the CNN paradigm and the CNN universal machine architecture and (3) the general principles of retinal modelling in CNN. Next we describe new CNN circuit and template design innovations that can be used to implement physiological functions in the retina and other sensory organs using the CNN universal machine. Finally we show how to combine given retinal functional elements implemented in the CNN universal machine with analogic algorithms to form the bionic retina. the resulting system can be used not only for simulating biological retinal function but also for generating functions that go far beyond biological capabilities. Several bionic retina functions, different topographic modalities and analogic CNN algorithms can then be combined to form the analogic CNN bionic eye. the qualitative aspects of the models, especially the range of dynamics and accuracy considerations in VLSI optoelectronic implementations, are outlined. Finally, application areas of the bionic eye and possibilities of constructing innovative devices based on this invention (such as the bionic eyeglass or the visual mouse) are described.     

DYNAMIC ANALOGIC CNN ALGORITHMS FOR A COMPLEX RECOGNITION TASK—A FIRST STEP TOWARDS A BIONIC EYEGLASS

Complex, dynamic, analogic CNN algorithms are presented for detecting some objects and features in a natural scene. Though the problem is well defined, the variations in the arrangements of features and objects and the illumination cause significant problems. The task is to find doors, door-handles, signs, etc. in a given floor of a house. The solution is a first step towards making a bionic CNN eyeglass.     

Cellular neural networks with non-linear and delay-type template elements and non-uniform grids

The cellular neural network (CNN) paradigm is a powerful framework for analogue non-linear processing arrays placed on a regular grid. In this paper we extend the current repertoire of CNN cloning template elements (atoms) by introducing additional non-linear and delay-type characteristics. In addition, architectures with non-uniform processors and neighbourhoods (grid sizes) are introduced. With this generalization, several well-known and powerful analogue array-computing structures can be interpreted as special cases of the CNN. Moreover, we show that the CNN with these generalized cloning templates has a general programmable circuit structure (a prototype machine) with analogue macros and algorithms. the relations with the cellular automaton (CA) and the systolic array (SA) are analysed. Finally, some robust stability results and the state space structure of the dynamics are presented.     

Cellular neural networks with opposite‐sign templates for image thinning

This paper presents image thinning algorithms using cellular neural networks (CNNs) with one‐ or two‐dimensional opposite‐sign templates (OSTs) as well as non‐unity gain output functions. Two four‐layer CNN systems with one‐dimensional (1‐D) OSTs are proposed for image thinning with 4‐ or 8‐connectivity, respectively. A CNN system, which consists of an eight‐layer CNN with two‐dimensional (2‐D) OSTs followed by another four‐layer CNN with 2‐D OSTs, is constructed for image thinning with 8‐connectivity, in which designs of B‐ and I‐templates are simpler than in CNNs with 1‐D OSTs. In the aforementioned designs, parameter values of 1‐D OSTs are chosen to make CNNs operate with thinning‐like property 1 (TL‐1), and those of 2‐D OSTs with 2‐D thinning‐like property (2‐DTL). Simulation studies show that these CNN systems have a good image thinning performance. Copyright © 1999 John Wiley & Sons, Ltd.     

Analogic CNN algorithms for textile applications

Some novel CNN analogic algorithms are proposed, which are useful in the context of textile industry. They concern the detection of stains and defects, and the recognition of the labels on a cloth. Copyright © 2000 John Wiley & Sons, Ltd.     

ANALOGUE COMBINATORICS AND CELLULAR AUTOMATA—KEY ALGORITHMS AND LAY-OUT DESIGN

This paper demonstrates how certain logic and combinatorial tasks can be solved using CNNs. A design method is proposed for solving combinatorial tasks on a CNN. It can be used to simulate cellular automata on a CNN, to prove the self-reproducing capability of the CNNUM and for sorting, histogram calculation, parity analysis and minimum Hamming distance computation. These solutions are especially useful since they can serve as subroutines of more complex CNNUM algorithms. As an important real-life application the lay-out of printed circuit boards is designed with the CNNUM at an extremely high speed.     

Object-oriented image analysis for very-low-bitrate video-coding systems using the CNN universal machine

The CNN universal machine (CNNUM) is applied to object-oriented video compression and proves its universality for future applications in the field of very-low-bitrate coding. This proposal joins recent work of Venetianer and Roska in unfolding the enormous computational abilities of the CNNUM for a wide class of video compression techniques. Here a novel image analysis technique is considered and realized in the form of analogic CNN algorithms. The specific features of the scheme, among them the extensive use of dynamic (finite running time) CNN cloning templates, are outlined and discussed through different computer simulations. When implemented on the CNNUM, its performances outdo those of equivalent digital systems and qualify the CNNUM as a serious competitor for future video coding hardware. © 1997 John Wiley & Sons, Ltd.     

CNN‐based architecture for real‐time object‐oriented video coding applications

This paper presents a new CNN‐based architecture for real‐time video coding applications. The proposed approach, by exploiting object‐oriented CNN algorithms and MPEG encoding capabilities, enables low bit‐rate encoder/decoder to be designed. Simulation results using Claire video sequence show the effectiveness of the proposed scheme. Copyright © 2005 John Wiley & Sons, Ltd.     

BP学习算法在CNN发电机建模中应用

在应用混沌神经网络(CNN)进行同步发电机的建模过程中,对于CNN的学习,网络训练过程的收敛性很难控制。在研究了BP学习算法及其一些改进方法进行人工神经网络训练的轨迹收敛特性后,观测到运用梯度下降动量与自适应学习速率相结合的BP学习算法的神经网络训练轨迹的收敛特性良好。在用基于Aihara混沌神经元构成的3层反馈CNN进行同步发电机建模的应用中,用该BP学习算法对CNN进行了训练。结果表明:用该BP算法进行CNN发电机建模具有学习速度快和均方误差曲线轨迹收敛性好的特点,而且所建立的CNN同步发电机模型运行的动态过程误差小。     

Robot vision with cellular neural networks: a practical implementation of new algorithms

Cellular neural networks (CNNs) are well suited for image processing due to the possibility of a parallel computation. In this paper, we present two algorithms for tracking and obstacle avoidance using CNNs. Furthermore, we show the implementation of an autonomous robot guided using only real‐time visual feedback; the image processing is performed entirely by a CNN system embedded in a digital signal processor (DSP). We successfully tested the two algorithms on this robot. Copyright © 2006 John Wiley & Sons, Ltd.     

基于字符级CNN的调水工程巡检文本智能分类方法

日常安全巡检是维护长距离调水工程安全运行的重要手段.目前巡检采集的非结构化文本数据主要依靠人工进行安全等级评判,在工作效率和准确率方面存在明显不足.本研究基于自然语言处理技术,提出了一种面向字符层面的卷积神经网络的巡检安全文本智能分类方法.该方法通过引入预训练的单个字符向量改进卷积神经网络的输入层,使得分类模型直接从原...     

CNN-based difference-controlled adaptive non-linear image filters

In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical–statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given throughout the text using various intensity images. © 1998 John Wiley & Sons, Ltd.     

基于seq2seq模型的非侵入式负荷分解算法

非侵入式负荷分解对于节能减排、负荷调峰、智能用能等方面均具有重要的现实意义。针对目前非侵入式负荷分解方法在低频采样条件下（1Hz及以下）分解准确率较低的问题,提出了一种基于卷积神经网络(CNN)与长短期记忆网络(LSTM)相结合的seq2seq的非侵入式负荷分解算法(seq2seq Based on CNN and LSTM,seq2seqBCL)。该模型将功率时间序列作为网络的输入,通过CNN做特征提取。考虑到电力数据的时序性,增加了LSTM层进行电器识别,相比于NILMTK中seq2seq模型降低了网络层数,简化了网络结构。在REDD数据集上对算法性能进行了评估,所提出的算法提升了整个网络系统的性能,与FHMM、CO和传统seq2seq算法相比,负荷分解准确率有明显提升。     

基于卷积神经网络和直接转矩控制的永磁同步电机模型预测转矩控制策略

模型预测转矩控制(MPTC)需要遍历所有备选电压矢量进行预测计算,从中选择最优电压矢量,控制性能良好,但算法计算量大和实时性差。采集MPTC的运行数据离线训练卷积神经网络(CNN),将训练好的CNN代替MPTC进行电压矢量选择。为了解决CNN失控问题,提出了基于CNN控制和直接转矩控制(DTC)的MPTC策略。仿真结果表明,该控制策略可有效解决CNN控制的失控问题,控制效果与MPTC基本相当,转矩和磁链脉动明显低于DTC。     

Blind signal separation using cellular neural networks

In this paper a two-layer cellular neural network (CNN) is used to separate blind signals. the topological structures of the CNN and the inner parameters are presented. the first CNN layer functions as an adaptive filter which converges asymptotically to an equilibrium point in the mean. A stochastic stability model is used to find conditions under which cells in the first layer converge. Conditions leading to correct equilibrium solutions are also presented using this model. the second CNN layer functions as a signal separator. Simulations show that the CNN blind signal separator has strong robustness and works even better than the theory predicts.     

Application of a cellular neural network to facial expression animation and high-level image processing

The cellular neural network (CNN) is used to animate facial expressions of a human being. First, the change in facial expressions is regarded as a smooth 2D transformation which is restricted by a bending energy function and displacements of some key-points. Second, the parameters of the CNN are determined by comparing the bending energy function with the energy function of the CNN. Finally, the CNN is used to realize the transformation by minimizing its energy function. Also, the CNN is used to model some visual illusions which are frequently used in psychological tests. First, the retinal induction field is modelled by using a template. The comparison of this CNN model with the real physiological measurements is presented. Then, based on this template, the CNN universal machine is used to model four types of visual illusions: subjective contour illusion (Kanizsa illusion), size illusion (Mueller-Lyer illusion, Ponzo illusion), direction and location illusion (angular illusion of location, Poggendorff illusion) and contrast illusion (Herring illusion). Computer simulations are provided for animating facial expressions and modelling visual illusions.     

船舶大功率发电机混沌神经网络建模

在分析和研究了Aihara神经元混沌特性的基础上,建立了基于Aihara混沌神经元的Elman局部递归混沌神经网络（CNN）,神经元引入混沌特性后增强了神经网络对非线性映射的全局逼近能力.在船舶大功率同步发电机建模中,以船用柴油机输出转矩功率和发电机输入励磁电流作为CNN建模与辨识的输入参数;以发电机的输出频率、发电机端电压和输出电流作为CNN建模与辨识的输出参数;采用有导师学习方式,运用基于BP的动态训练方法,最终完成了船舶大功率发电机的动态建模.与其它的ANN建模相比较,用CNN建立的模型的隐层神经元数量少,系统的泛化能力强.