A Hopfield neural network with multiple attractors and its FPGA design

Neural network is important for a wide range of applications. Especially, a small neural network can display various complex behaviors. In this work, the investigations of a Hopfield neural network and its field programmable gate array (FPGA) implementation have been reported. The considered Hopfield neural network is simple because it includes only three neurons. It is interesting that we observed chaos and numerous coexisting attractors in such a network. In addition, the network has been implemented via an FPGA platform to verify its feasibility.     

Image feature extraction by dynamic neural filtering and phase-only joint transform correlation

Neural network-based image processing algorithms present numerous advantages due to their supervised adjustable properties. Among various neural network architectures, dynamic neural networks, Hopfield and Cellular networks, have been found inherently suitable for filtering applications. Combining supervised and filtering features of dynamic neural networks, this paper presents dynamic neural filtering technique based on Hopfield neural network architecture. The filtering technique has also been implemented by using phase-only joint transform correlation (POJTC) for optical image processing applications. Filtering structure is basically similar to the Hopfield neural network structure except for the adjustable filter mask and 2D convolution operation instead of weight matrix operations. The dynamic neural filtering architecture has learnable properties by back-propagation learning algorithm. POJTC presents significant advantages to achieve the operation of summing the cross-correlation of bipolar data by phase-encoding bipolar data in parallel. The image feature extraction performance of the proposed optical system is reported for various image processing applications using a simulation program.     

Single Neuronal Dynamical System in Self-Feedbacked Hopfield Networks and Its Application in Image Encryption

Image encryption is a confidential strategy to keep the information in digital images from being leaked. Due to excellent chaotic dynamic behavior, self-feedbacked Hopfield networks have been used to design image ciphers. However, Self-feedbacked Hopfield networks have complex structures, large computational amount and fixed parameters; these properties limit the application of them. In this paper, a single neuronal dynamical system in self-feedbacked Hopfield network is unveiled. The discrete form of single neuronal dynamical system is derived from a self-feedbacked Hopfield network. Chaotic performance evaluation indicates that the system has good complexity, high sensitivity, and a large chaotic parameter range. The system is also incorporated into a framework to improve its chaotic performance. The result shows the system is well adapted to this type of framework, which means that there is a lot of room for improvement in the system. To investigate its applications in image encryption, an image encryption scheme is then designed. Simulation results and security analysis indicate that the proposed scheme is highly resistant to various attacks and competitive with some exiting schemes.     

Statistical tests and chaotic synchronization based pseudorandom number generator for string bit sequences with application to image encryption

Recently, a stream encryption scheme using d-bit segment sequences has been proposed. This scheme may generate key avalanche effect. The randomness tests of d-bit segment pseudorandom number generator will be important for implementing such a scheme. Firstly this paper extends Beker and Piper’s binary pseudorandom sequence statistical test suite to d-bit segment sequences case. Secondly, a novel 3-dimensional polynomial discrete chaotic map (3DPDCM) is proposed. The calculated Lyapunov exponents of the 3DPCDM are 0.213, 0.125 and ? 3.228. Using the 3DPDCM constructs a 6-dimensional generalized synchronization chaotic system. Based on this system, a 8-bit segment chaotic pseudorandom number generator (CPRNG) is introduced. Using the generalized test suite tests 100 key streams generated via the 8-bit PRNG with different initial conditions and perturbed system parameters. The tested results are similar to those of the key streams generated via RC4 PRNG. As an application, using the key streams generated via the CPRNG and the RC4 PRNG encrypts an RGB image Landscape. The results have shown that the encrypted RGB images have significant avalanche effects. This research suggests that the requirements for PRNGs are not as strict as those under the traditional avalanche criteria. Suitable designed chaos-based d-bit string PRNGs may be qualified candidates for the stream encryption scheme with avalanche effect.     

Modulo image encryption with fractal keys

An encryption technique based on the modulo operation is proposed. The technique is a one-to-one encryption–decryption single key algorithm. Fractal images are proposed to be used as a source of randomness to generate strong keys. The use of the proposed method is verified, both in the single image encryption–decryption, and in a real-time streaming application. The described algorithm provides a mechanism for controlling the strength of the keys. The advantages of the proposed method are discussed. A video setup is built and GUI software implemented to practically test this method. Numerical results of the test are provided and analyzed. Overall, the theoretically anticipated results are achieved, and the algorithm proven to be adept for real world cryptographic applications.     

A multi-directional controllable multi-scroll conservative chaos generator:Modelling,analysis,and FPGA implementation

Combing with the generalized Hamiltonian system theory,by introducing a special form of sinusoidal function,a class of n-dimensional(n=1,2,3)controllable multi-scroll conservative chaos with complicated dynamics is constructed.The dynamics characteristics including bifurcation behavior and coexistence of the system are analyzed in detail,the latter reveals abundant coexisting flows.Furthermore,the proposed system passes the NIST tests and has been implemented physically by FPGA.Compared to the multi-scroll dissipative chaos,the experimental portraits of the proposed system show better ergodicity,which have potential application value in secure communication and image encryption.     

混沌映射和神经网络互扰的新型复合流密码

提出了一种将新型的神经网络互学习模型和常见的多混沌系统融合互扰的复合流密码方案. 首先利用三个Logistics混沌映射产生的随机序列作为神经网络互学习模型中三个 隐含层神经元的随机输入, 神经网络交互学习达到内部权值同步后, 再将同步权值映射为随机序列并与三个Logistics序列复合产生最终的密钥流. 实验表明, 产生的密钥流具有更好的随机性, 混沌流加密应用效果好. 关键词： 混沌映射 神经网络 权值同步 随机密钥流     

Hybrid Control of Digital Baker Map with Application to Pseudo-Random Number Generator

Dynamical degradation occurs when chaotic systems are implemented on digital devices, which seriously threatens the security of chaos-based cryptosystems. The existing solutions mainly focus on the compensation of dynamical properties rather than on the elimination of the inherent biases of chaotic systems. In this paper, a unidirectional hybrid control method is proposed to improve the dynamical properties and to eliminate the biases of digital chaotic maps. A continuous chaotic system is introduced to provide external feedback control of the given digital chaotic map. Three different control modes are investigated, and the influence of control parameter on the properties of the controlled system is discussed. The experimental results show that the proposed method can not only improve the dynamical degradation of the digital chaotic map but also make the controlled digital system produce outputs with desirable performances. Finally, a pseudorandom number generator (PRNG) is proposed. Statistical analysis shows that the PRNG has good randomness and almost ideal entropy values.     

基于特征提取和脉冲耦合神经网络的图像融合算法

为了提高目标检测的准确度和精确度,提出了一种新的基于特征提取和脉冲耦合神经网络(Pulse-coupled neural network,PCNN)模型的融合算法。该算法的原理是:首先对原图像进行特征提取,然后分别建立基于处理后的图像及原图像的PCNN。融合的作用是通过PCNN的链接输入得以体现的。融合图像综合了各个侧重于原图像不同特征的滤波器的选择性。仿真结果证明,所提出的算法在增加图像目标的可识别程度方面效果明显。     

Chaos-based image encryption using a hybrid genetic algorithm and a DNA sequence

The paper studies a recently developed evolutionary-based image encryption algorithm. A novel image encryption algorithm based on a hybrid model of deoxyribonucleic acid (DNA) masking, a genetic algorithm (GA) and a logistic map is proposed. This study uses DNA and logistic map functions to create the number of initial DNA masks and applies GA to determine the best mask for encryption. The significant advantage of this approach is improving the quality of DNA masks to obtain the best mask that is compatible with plain images. The experimental results and computer simulations both confirm that the proposed scheme not only demonstrates excellent encryption but also resists various typical attacks.     

Hopfield neural network and its applications on image edge detection

A method of image edge detection using the Hopfield neural network (HNN) is proposed in this paper.The image edge parameters are introduced in detail, and the energy function of HNN is given based on the edge parameters. Tests on the image edge detection show that images detected by the proposed method have good edge closeness and true edge, at the same time it has good anti-noise performance. The image edge detection using HNN is better than that obtained by some other edge detection operators.     

基于动态混沌映射的三维加密正交频分复用无源光网络

提出了一种基于混沌映射的三维加密正交频分复用无源光网络保密通信系统.该系统通过相关性检测锁定收发端混沌系统参数,实现收发双方混沌系统同步;并利用同步混沌系统生成密钥,实现符号扰动以及二重子载波加密.该加密方案的密钥空间超过10~(86),能够有效对抗穷举攻击.实验实现了13.3 Gb/s基于64进制正交幅度调制的加密正交频分复用信号在25 km标准单模光纤中的传输,并完成了信息的有效解密.     

基于CNN的红外图像边缘检测算法的FPGA实现

提出了一种以现场可编程门阵列为硬件处理器实现基于细胞神经网络的红外图像边缘检测方法.首先利用simulink的算法行为特性搭建红外图像输入模块,获得相关的红外图像头信息并对红外图像像素值范围进行相应变化,然后根据细胞神经网络模板所创建的查找表设计单个细胞元软核,再利用细胞神经网络阵列的规则性和互联的局域性,将单个细胞元软核扩展成细胞神经网络阵列.最后采用modelsim将细胞神经网络阵列与红外图像输入、输出模块相关联,从而达到实时处理的效果.实验结果表明:基于现场可编程门阵列为硬件处理器平台实现的细胞神经网络对红外图像进行边缘检测取得了较好的效果,且与MATLAB软件仿真的结果进行对比得出两者只有极其微小的差别.在Xilinx公司Virtex-6系列的现场可编程门阵列平台上,综合后占用极少资源的情况下得到142.693 MHz的最高频率,并且达到了2.378 Mpixels/sec处理速度.     

基于CNN的红外图像边缘检测算法的FPGA实现

提出了一种以现场可编程门阵列为硬件处理器实现基于细胞神经网络的红外图像边缘检测方法.首先利用simulink的算法行为特性搭建红外图像输入模块,获得相关的红外图像头信息并对红外图像像素值范围进行相应变化,然后根据细胞神经网络模板所创建的查找表设计单个细胞元软核,再利用细胞神经网络阵列的规则性和互联的局域性,将单个细胞元软核扩展成细胞神经网络阵列.最后采用modelsim将细胞神经网络阵列与红外图像输入、输出模块相关联,从而达到实时处理的效果.实验结果表明:基于现场可编程门阵列为硬件处理器平台实现的细胞神经网络对红外图像进行边缘检测取得了较好的效果,且与MATLAB软件仿真的结果进行对比得出两者只有极其微小的差别.在Xilinx公司Virtex-6系列的现场可编程门阵列平台上,综合后占用极少资源的情况下得到142.693 MHz的最高频率,并且达到了2.378 Mpixels/sec处理速度.     

A novel image block cryptosystem based ona spatiotemporal chaotic system and a chaotic neural network

In this paper, we propose a novel block cryptographic scheme based on a spatiotemporal chaotic system and a chaotic neural network (CNN). The employed CNN comprises a 4-neuron layer called a chaotic neuron layer (CNL), where the spatiotemporal chaotic system participates in generating its weight matrix and other parameters. The spatiotemporal chaotic system used in our scheme is the typical coupled map lattice (CML), which can be easily implemented in parallel by hardware. A 160-bit-long binary sequence is used to generate the initial conditions of the CML. The decryption process is symmetric relative to the encryption process. Theoretical analysis and experimental results prove that the block cryptosystem is secure and practical, and suitable for image encryption.     

Image watermarking capacity analysis based on Hopfield neural network

In watermarking schemes, watermarking can be viewed as a form of communication problems. Almost all of previous works on image watermarking capacity are based on information theory, using Shannon formula to calculate the capacity of watermarking. In this paper, we present a blind watermarking algorithm using Hopfield neural network, and analyze watermarking capacity based on neural network. In our watermarking algorithm, watermarking capacity is decided by attraction basin of associative memory.     

局域互联神经网络的关联存储

基于全局互联的Hopfield模型,本文提出了局域互联关联存储的新概念.与全局互联相比,局域互联具有较小的关联矩阵,因而,有利于用现有的空间光调制器加以实现.同时,计算机模拟结果表明,它仍然具有全局关联存储的能力.     

Image fusion scheme using a novel dual-channel PCNN in lifting stationary wavelet domain

This paper presents a new multi-source image fusion scheme based on lifting stationary wavelet transform (LSWT) and a novel dual-channel pulse-coupled neural network (PCNN). By using LSWT, we can calculate a flexible multiscale and shift-invariant representation of registered images. After decomposing the original images using LSWT, a new dual-channel pulse coupled neural network, which can overcome some shortcomings of original PCNN for image fusion and putout the fusion image directly, is proposed and used for the fusion of sub-band coefficients of LSWT. In this fusion scheme, a new sum-modified-laplacian(NSML) of the low frequency sub-band image, which represent the edge-feature of the low frequency sub-band image in SLWT domain, is presented and input to motivate the dual-channel PCNN. For the fusion of high frequency sub-band coefficients, a novel local neighborhood modified-laplacian (LNML) measurement is developed and used as external stimulus to motivate the dual-channel PCNN. This fusion scheme is verified on several sets of multi-source images, and the experiments show that the algorithms proposed in the paper can significantly improve image fusion performance, compared with the fusion algorithms such as traditional wavelet, LSWT, and LSWT-PCNN in terms of objective criteria and visual appearance.     

A novel cellular automata based technique for visual multimedia content encryption

This paper proposes a new method for visual multimedia content encryption using Cellular Automata (CA). The encryption scheme is based on the application of an attribute of the CLF XOR filter, according to which the original content of a cellular neighborhood can be reconstructed following a predetermined number of repeated applications of the filter.The encryption is achieved using a key image of the same dimensions as the image being encrypted. This technique is accompanied by the one-time pad (OTP) encryption method, rendering the proposed method reasonably powerful, given the very large number of resultant potential security keys. The method presented here makes encryption possible in cases where there is more than one image with the use of just one key image. A further significant characteristic of the proposed method is that it demonstrates how techniques from the field of image retrieval can be used in the field of image encryption. The proposed method is further strengthened by the fact that the resulting encrypted image for a given key image is different each time. The encryption result depends on the structure of an artificial image produced by the superposition of four 1-D CA time-space diagrams as well as from a CA random number generator.A semi-blind source separation algorithm is used to decrypt the encrypted image. The result of the decryption is a lossless representation of the encrypted image. Simulation results demonstrate the effectiveness of the proposed encryption method. The proposed method is implemented in C# and is available online through the img(Rummager) application.     

基于幅值相位型离散Hopfield神经网络的多进制振幅键控盲检测

针对统计量算法盲检测多进制振幅键控(MPSK)信号的缺陷, 提出了一种幅值相位型连续多值复数Hopfield神经网络算法, 构造了适用于MPSK信号的幅相型离散多电平激活函数,并分别在异步和同步更新模式下证明了该神经网的稳定性.当该神经网的权矩阵借助接收数据补投影算子构成时, 该幅相型离散Hopfield神经网络可有效地实现MPSK信号盲检测. 仿真试验表明:该算法所需接收数据较短,可到达全局真解点,并且适用于含公零点信道.