一种基于小波变换的跨带矢量量化

由小波变换产生的子带之间存在着较强的相关性,然而目前的在基于小波变换的图像编码矢量量化中,码矢往往仅由带内系数组成,没有充分利用带间相关性。本文提出一种新的跨带矢量量化算法,码矢由在同级子带中的相应系数组成。在三次小波变换下,第一级子带的码矢维数为４８Ｄ,第二级为１２Ｄ,第三级为３Ｄ。这样形成的码矢既匹配了各级子带的重要性,又利用到了带内和带间相关性,在相同的比特率下,其重构图像的信噪比ＰＳＮＲ比码矢仅由带内系数组成的传统带内ＶＱ高出１～２ｄＢ。     

基于神经网络的图像识别方法研究

图像识别涉及大量的信息运算,要求处理速度快、识别精度高,神经网络的实时性和容错性要符合图像识别的要求。利用改进的BP神经网络算法对旋转畸变图像进行了定位和识别,改进算法将附加动量项与自适应学习速率相结合,有效地抑制了网络陷入局部极小点,提高了网络的训练速度。结果表明,基于神经网络的图像识别方法是有效的、可行的。     

基于一种改进的比特分配算法的小波变换矢量量化

本文通过引进视觉加权对Ｗｅｓｔｅｒｉｎｋ的优化比特分配算法作了改进；用改进后的比特分配算法于小汉变换矢量量化。获得了较好的编码结果。     

图样间联想光学神经网络模型存贮分析及两层异联想识别模型的构造

本文详细讨论了图样间联想网络的最大存贮容量,给出了实现图样间异联想的两个充分条件.在此基础上,利用改进的图样间异联想算法构造了两层异联想模型(THA)用于图样识别,网络判辨率与恢复率较图样间自联想识别均有很大提高;且其互连权矩阵更加简单稀疏并可平面化,光学实现更为简便.     

一种矢量量化编码的快速搜索算法

提出了一种矢量量化编码的快速匹配算法。利用码书的拓扑结构和柯西 施瓦兹不等式的性质推导出了消除不必要匹配操作的条件,并根据这个条件提出了快速搜索算法。实验结果表明,该算法不仅明显降低了矢量编码过程的复杂程度,同时也保证了与全搜索编码相同的图像编码质量。与其它搜索方法的操作次数和存储空间进行了比较。     

改进自适应LBG矢量量化算法在干涉高光谱图像压缩中的应用

在基于点到线模型扩展LBG(linde-buzo-gray algorithm)矢量量化算法的基础上,提出了一种更为高效的新型自适应LBG矢量量化算法,并给出了该算法在干涉高光谱图像无损压缩中的实际压缩方案.该算法在LBG算法码书中利用点到线的垂线关系基础上进行了改进,执行进一步的自适应化迭代进而获得了更小的残差.将自...     

基于Karhunen-Loève变换和小波谱特征矢量量化的三维谱像数据压缩

提出了基于Karhunen Lo埁ｖｅ变换的小波谱特征矢量量化三维谱像数据压缩方法耍幔颍瑁酰睿澹?Lo埁ｖｅ变换 /小波变换 /小波谱特征矢量量化方法应用了Karhunen Lo埁ｖｅ变换的消除谱相关性优良性能 ,应用二维小波变换消除空间相关性 ,在小波变换域内应用二维集分割嵌入块编码和一维谱特征矢量量化对三维谱像数据压缩 ,获得较高的压缩性能。实验结果表明 :Karhunen Lo埁ｖｅ变换 /小波变换 /小波谱特征矢量量化编码比Karhunen Lo埁ｖｅ变换 /小波变换 /改进对块零树编码和Karhunen Lo埁ｖｅ变换 /小波变换 /快速矢量量化编码方法在同样压缩比条件下 ,峰值信噪比提高 2dB和 1dB以上 ,而速度提高了 1.5和 8倍 ,整体压缩性能有较大的提高     

Hopfield神经网络模型的恢复特性

通过引入不同概率的双峰无规神经激活阈分布,来考虑对神经网络“记忆”恢复特性的影响,结果表明即使储存模式数超过孤立Hopfield模型的临界值α_c时系统仍然能成功地恢复储存信息。 关键词：     

基于Gabor遗传算法的红外图像识别

本文提出了一种基于Gabor小波的遗传算法。这种算法对于影像复杂、噪声强烈的红外图像有着独特的特征提取和特征融合作用，因而大大提高了图像收敛速度和识别效率。文章最后给出了仿真实例，证明了该算法的可行性。     

基于数学形态谱和二维矢量分类网络的模式识别及二维矢量分类网络的光学实现

介绍一种基于数学形态谱和二维矢量分类网络的模式识别体系。数学形态谱相对于图像平移和旋转不变。建立了光学二维矢量分类网络，利用光学逻辑操作和最大值网络的循环操作，得到与输入图像最佳匹配的模式。     

A Remot Sensing Image Compression Method Based on Wavelet Transformation/Vector Quantization

1.IntroductionVectorquantizationprovidesameansofconvertingthedecomposedsignalintobitsinamannerthattakesadvantageofremaininginter--andinter--bandcorrelationaswellasofthemoreflexiblepartitionsofhigherdimensionalvectorspaces.TheimagecompressionmethodofWT VQhasbeenappliedinmanydigitalimageprocessingfields.SubbandcodingwasintroducedbyCroisieretal.inspeechcodingin197611].Croisieretal.firstsolvedthecriticalproblemofaliasingcancellationaf:erdecimationandreconstructioninsubbands,using"Quadraturemirr…     

Fast Encoding Method for Image Vector Quantization Based on Multiple Appropriate Features to Estimate Euclidean Distance

The encoding process of finding the best-matched codeword (winner) for a certain input vector in image vector quantization (VQ) is computationally very expensive due to a lot of k-dimensional Euclidean distance computations. In order to speed up the VQ encoding process, it is beneficial to firstly estimate how large the Euclidean distance is between the input vector and a candidate codeword by using appropriate low dimensional features of a vector instead of an immediate Euclidean distance computation. If the estimated Euclidean distance is large enough, it implies that the current candidate codeword could not be a winner so that it can be rejected safely and thus avoid actual Euclidean distance computation. Sum (1-D), L₂ norm (1-D) and partial sums (2-D) of a vector are used together as the appropriate features in this paper because they are the first three simplest features. Then, four estimations of Euclidean distance between the input vector and a codeword are connected to each other by the Cauchy–Schwarz inequality to realize codeword rejection. For typical standard images with very different details (Lena, F-16, Pepper and Baboon), the final remaining must-do actual Euclidean distance computations can be eliminated obviously and the total computational cost including all overhead can also be reduced obviously compared to the state-of-the-art EEENNS method meanwhile keeping a full search (FS) equivalent PSNR.     

Power law decay of stored pattern stability in sparse Hopfield neural networks

Hopfield neural networks on scale-free networks display the power law relation between the stability of patterns and the number of patterns.The stability is measured by the overlap between the output state and the stored pattern which is presented to a neural network.In simulations the overlap declines to a constant by a power law decay.Here we provide the explanation for the power law behavior through the signal-to-noise ratio analysis.We show that on sparse networks storing a plenty of patterns the stability of stored patterns can be approached by a power law function with the exponent-0.5.There is a difference between analytic and simulation results that the analytic results of overlap decay to 0.The difference exists because the signal and noise term of nodes diverge from the mean-field approach in the sparse finite size networks.     

Theoretical analysis and computer simulations of the second-order Hopfield model

Theoretical analyses of the second-order Hopfield model show that the second-order Hopfield model with the bipolar binary (-1,1) vectors will have better than the samemodel with the unipolar binary (0,1) vectors.Computer simulations given in this paper con-firm this conclusion.     

A Novel Color Image Encryption Scheme Based on Hyperchaos and Hopfield Chaotic Neural Network

Problems such as insufficient key space, lack of a one-time pad, and a simple encryption structure may emerge in existing encryption schemes. To solve these problems, and keep sensitive information safe, this paper proposes a plaintext-related color image encryption scheme. Firstly, a new five-dimensional hyperchaotic system is constructed in this paper, and its performance is analyzed. Secondly, this paper applies the Hopfield chaotic neural network together with the novel hyperchaotic system to propose a new encryption algorithm. The plaintext-related keys are generated by image chunking. The pseudo-random sequences iterated by the aforementioned systems are used as key streams. Therefore, the proposed pixel-level scrambling can be completed. Then the chaotic sequences are utilized to dynamically select the rules of DNA operations to complete the diffusion encryption. This paper also presents a series of security analyses of the proposed encryption scheme and compares it with other schemes to evaluate its performance. The results show that the key streams generated by the constructed hyperchaotic system and the Hopfield chaotic neural network improve the key space. The proposed encryption scheme provides a satisfying visual hiding result. Furthermore, it is resistant to a series of attacks and the problem of structural degradation caused by the simplicity of the encryption system’s structure.     

Deformation Quantization of Hermitian Vector Bundles

Motivated by deformation quantization, we consider in this paper *-algebras over rings = (i), where is an ordered ring and I²=–1, and study the deformation theory of projective modules over these algebras carrying the additional structure of a (positive) -valued inner product. For A=C (M), M a manifold, these modules can be identified with Hermitian vector bundles E over M. We show that for a fixed Hermitian star product on M, these modules can always be deformed in a unique way, up to (isometric) equivalence. We observe that there is a natural bijection between the sets of equivalence classes of local Hermitian deformations of C (M) and ( (E)) and that the corresponding deformed algebras are formally Morita equivalent, an algebraic generalization of strong Morita equivalence of C ^*-algebras. We also discuss the semi-classical geometry arising from these deformations.     

Improving Associative Memory Function in the Steepest Descending Asynchronous Network with Tunneling Rule

In this paper effects of a new evolutionary rule added to the dynamics of the steepest descending asynchronous network model were studied. By numerical simulations, we found that the neural network operates very efficiently to improve the fault-tolerance when ,its capacity a ≤ 1 under the new rule. The simulations were conducted on both the low- and the highdimensional networks. A modified training scheme is also introduced.     

Influence of Blurred Ways on Pattern Recognition of a Scale-Free Hopfield Neural Network

We investigate the influence of blurred ways on pattern recognition of a Barabasi-Albert scale-free Hopfield neural network （SFHN） with a small amount of errors. Pattern recognition is an important function of information processing in brain. Due to heterogeneous degree of scale-free network, different blurred ways have different influences on pattern recognition with same errors. Simulation shows that among partial recognition, the larger loading ratio （the number of patterns to average degree P/ （k） ） is, the smaller the overlap of SFHN is. The influence of directed （large） way is largest and the directed （small） way is smallest while random way is intermediate between them. Under the ratio of the numbers of stored patterns to the size of the network PIN is less than O. 1 conditions, there are three families curves of the overlap corresponding to directed （small）, random and directed （large） blurred ways of patterns and these curves are not associated with the size of network and the number of patterns. This phenomenon only occurs in the SFHN. These conclusions are benefit for understanding the relation between neural network structure and brain function.     

基于可见光谱和支持向量机的黄瓜叶部病害识别方法研究

以黄瓜叶部病害作为研究对象,基于可见光谱反射率差异识别黄瓜叶部病害,研究基于SVM的黄瓜叶部病害识别预测模型。采用小波变换进行数据预处理;选取Otsu、边缘分割法和K均值聚类三类分割方法进行病斑分割,比较错分率和运行时间,K均值聚类方法更适合黄瓜叶部病斑分割;提取纹理、颜色和形状特征参数,共15个特征参数;通过交叉验证选择最优参数c和g,对核函数参数进行优化处理,并通过比较线性核、多项式核、RBF核等不同核函数情况下SVM的正确识别率,确定RBF核SVM模式识别方法能够更精准地识别黄瓜叶部病害。并将基于SVM与另外两种常见的黄瓜叶部病害识别方法,BP神经网络和模糊聚类进行比较,结果表明,基于SVM的识别模型对霜霉病的正确识别率为95%,白粉病和褐斑病的正确识别率均为90%,平均诊断正确率为92%;该模式识别方法识别效果最佳,运行时间最短,为基于可见光谱的黄瓜病害识别模型提供参考。