基于小波域的深度残差网络图像超分辨率算法

单幅图像超分辨率（SISR）是指从一张低分辨率图像重建高分辨率图像.传统的神经网络方法通常在图像的空间域进行超分辨率重构，但这些方法常在重构过程中忽略重要的细节.鉴于小波变换能够将图像内容的"粗略"和"细节"特征进行分离，提出一种基于小波域的深度残差网络（DRWSR）.不同于其他传统的卷积神经网络直接推导高分辨率图像（HR），该方法采用多阶段学习策略，首先推理出高分辨率图像对应的小波系数，然后重建超分辨率图像（SR）.为了获取更多的信息，该方法采用一种残差嵌套残差的灵活可扩展的深度神经网络.此外，提出的神经网络模型采用结合图像空域与小波域的损失函数进行优化求解.所提出的方法在Set5、Set14、BSD100、Urban100等数据集上进行实验，实验结果表明，该方法的视觉效果和峰值信噪比（PSNR）均优于相关的图像超分辨率方法.     

An expert system based on wavelet decomposition and neural network for modeling Chua’s circuit

This paper presents an expert system based on wavelet decomposition and neural network for modeling and simulation of Chua’s circuit which is used for chaos studies. The problems which arise in modeling Chua’s circuit by neural networks are high structural complexity and slow and difficult training. With this proposed method a new solutions is produced to solve these problems. Wavelet decomposition is used for new useful feature extracting from input signal and neural network is used for modeling. Test results of proposed wavelet decomposition and neural network model are compared with test results of neural network model. Desired performance is provided by this new model. Test results showed that the suggested method can be used efficiently for modeling nonlinear dynamical systems.     

Across-scale process similarity based interpolation for image super-resolution

A pivotal step in image super-resolution techniques is interpolation, which aims at generating high resolution images without introducing artifacts such as blurring and ringing. In this paper, we propose a technique that performs interpolation through an infusion of high frequency signal components computed by exploiting ‘process similarity’. By ‘process similarity’, we refer to the resemblance between a decomposition of the image at a resolution to the decomposition of the image at another resolution. In our approach, the decompositions generating image details and approximations are obtained through the discrete wavelet (DWT) and stationary wavelet (SWT) transforms. The complementary nature of DWT and SWT is leveraged to get the structural relation between the input image and its low resolution approximation. The structural relation is represented by optimal model parameters obtained through particle swarm optimization (PSO). Owing to process similarity, these parameters are used to generate the high resolution output image from the input image. The proposed approach is compared with six existing techniques qualitatively and in terms of PSNR, SSIM, and FSIM measures, along with computation time (CPU time). It is found that our approach is the fastest in terms of CPU time and produces comparable results.     

利用图像局部自相似性的超分辨率重构算法

图像超分辨率重构是指由低分辨率图像来获得高分辨率图像的过程。为了能够有效地重构出高分辨率图像,提出一种基于图像局部自相似性的超分辨率快速重构算法。该算法首先利用四叉树分割的知识对低分辨率图像进行自适应分块;然后利用低分辨率图像和高分辨率图像在局部区域内的自相似性,由最小二乘方法在各个局部区域自适应的选择插值所需的参数,从而在各个局部区域内进行插值;最后运用小波域的投影算子对插值得到的高分辨率图像进行全局优化,得到最终的高分辨率图像。实验结果表明,由该算法重构的高分辨图像有很好的视觉效果和峰值信噪比。     

基于BP神经网络的图像插值算法研究

图像插值技术具有重要的研究价值。本文提出了一种结合BP神经网络、小波变换、线性插值的图像放大算法,提高图像分辨率。实验结果表明:该方法获得的高分辨率图像主观上拥有良好的视觉效果,客观上具有较高的峰值信噪比(PSNR),并且较好地保留了图像细节,边缘模糊和阶梯形失真也明显降低。因此,使用本文插值算法获得高分辨率图像是可行的。     

一种融合小波变换与卷积神经网络的高相似度图像识别与分类算法

针对特定领域高相似度图像识别与分类问题,提出融合小波变换与卷积神经网络的高相似度图像识别与分类算法。首先,利用小波变换提取图像纹理特征,对不同类别、不同分辨率图像集进行训练并确定最佳纹理差异度参数值;其次,根据纹理差异度运用小波分解方法对图像进行子图分解,提取各子图能量特征并进行归一化处理;接着,通过卷积神经网络5层卷积和3层池化交替,将输入图像特征向量转化为一维向量;最后,通过训练次数的增加以及数据量的增大,不断优化网络参数,提高在训练集中的分类准确度,在测试集中验证权值实际准确度,得到具有最高分类准确率的卷积神经网络模型。实验选取鸡蛋、苹果两类图像数据集作为实验数据,进行鸡蛋散养或圈养识别、苹果产地判定,实验结果表明：该算法平均鉴别准确率均达90%以上。     

An HVS-Directed Neural-Network-Based Image Resolution Enhancement Scheme for Image Resizing

In this paper, a novel human visual system (HVS)-directed neural-network-based adaptive interpolation scheme for natural image is proposed. A fuzzy decision system built from the characteristics of the HVS is proposed to classify pixels of the input image into human perception nonsensitive class and sensitive class. Bilinear interpolation is used to interpolate the nonsensitive regions and a neural network is proposed to interpolate the sensitive regions along edge directions. High-resolution digital images along with supervised learning algorithms are used to automatically train the proposed neural network. Simulation results demonstrate that the proposed new resolution enhancement algorithm can produce a higher visual quality for the interpolated image than the conventional interpolation methods.     

基于改进ResNet-50的图像特征提取网络

为了提高图像的特征质量,保证最后提取到的特征高度精炼,提出了一种新的方法;该方法首先将低分辨率图像经过小波变换分解成高频分量和低频分量,并结合插值法进行插值,最后通过小波逆变换得到高分辨率图像来为后续的特征提取提供高质量的图片输入;接着,选取ResNet-50网络作为基础网络,将Efficient Channel Attention(ECA)模块与ResNet残差结构结合形成一个全新的ECA-ResNet50模块,ECA模块具有的通道级的注意力机制,可以让整个网络更加专注于提取显著特征;经实验测试,该方法对于图像特征提取的质量有着明显的提升,均方误差下降可达6.65;结果表明,该方法可行有效,具有良好的工程应用前景;     

基于小波变换和神经网络的车内噪声信号重构

为获取较高精度车内噪声主动控制(Active Noise Control, ANC)参考信号,提出了一种基于小波变换和BP神经网络的车内噪声信号重构方法。以在某轿车采集到的噪声信号为基础,用声学传递路径分析(TPA)方法确定影响车内噪声的关键点信号。鉴于噪声源信号对车内信号非线性关系的复杂性,建立BP神经网络的噪声重构模型,并利用小波分解来降低噪声信号的非平稳性。为对比重构效果,建立BP神经网络噪声重构模型。结果表明,本文提出算法的重构值与实测值之间的平均绝对误差比BP神经网络小,并且基于小波变换和BP网络重构模型的平均绝对误差均小于0.01。该方法能够对车内噪声信号进行准确、有效的重构。     

基于小波神经网的SAR图像识别算法

针对SAR图像的自动目标识别问题,研究了基于小波分析和神经网络的识别算法.由非线性小波基作为网络中神经元的激励函数,隐层结点数由小波分解次数和处理目标类别数决定,输出层由目标的类别数决定,同时利用目标的方位角来限定被识别目标的范围.实验结果表明,该方法有效降低了训练和识别的难度,取得了优于BP网络的识别结果,具有广阔的应用前景.     

基于分割的图像超分辨率重构算法

鉴于当前算法不能很好解决重构效果和算法复杂度之间的矛盾,提出了一种基于分割的图像超分辨率重构算法.首先提出了一种基于纹理的图像分割方法,将图像分为纹理较多和较少两个区域,然后针对纹理较少区域提出了改进型小波多尺度插值方法,纹理较多区域提出了固定训练集神经网络方法.本算法综合了小波方法的简单性和神经网络方法的精确性.实验结果表明,新算法重构效果良好,复杂度较低,操作性好.     

多抽样率小波信号分解

在信号分析过程中,用二进小波对信号进行分解以便观察信号在不同子带内的时频特征是一种非常有效的时频分析方法。但由于受信号采样频率的限制,往往使所感兴趣的信号分量不能完整地出现在某一子带内。既使是提高小波分解层数或者用小波包技术也不能很好地解决这一问题。文章提出多抽样率小波信号分解方法,该方法根据目标信号的频带宽度,通过对原始信号的插值和抽取改变抽样频率,以实现不同子带分量的分离。     

一种人工神经网络算法在汽车防撞雷达中的应用

将人工神经网络的方法用于汽车防撞雷达中的信号处理,该方法基于自相关矩阵分解,通过对Hopfield神经网络能量函数变换,将分解问题转化为一个简单的迭代问题来求解。该方法可用来替代传统的FFT方法,以实现对目标距离的超分辨提取。通过计算机仿真和硬件系统的实际测试研究了它的性能,并与AR算法、MUSIC算法进行了比较,结果表明该方法具有更好的信噪比和分辨性能。     

基于脉冲耦合神经网络的异源图像融合方法

针对基于主成分分析与二代小波变换的图像融合算法中鲁棒性不高、融合图像质量较低的问题,提出了基于鲁棒性主成分分析与脉冲耦合神经网络的融合方法.所提出的算法将可见光与红外图像进行二代小波变换,转换为高频与低频信号,接着采用不同的融合策略针对低频和高频信号进行融合.针对低频信号,利用鲁棒性主成分分析法还原低秩矩阵并采用加权平均的融合策略进行融合;针对高频信号,将其送入至脉冲神耦合神经网络中进行融合得到融合后的小波系数.将融合后的小波系数进行逆变换,得到最终融合图像.实验结果表明,相比于基于主成分分析与二代小波变换的图像融合算法,利用所提出的出算法得到的融合图像中熵指标、空间频率指标、结构相似度指标和峰值信噪比指标均得到了不同程度的提升.因此,所提出的算法能够更好地提取目标信息,使融合图像中目标的轮廓边缘更加清晰,同时将提升小波分解出的高频信息利用PCNN进行融合,更加突出细节信息.     

A new optimum feature extraction and classification method for speaker recognition: GWPNN

Speech and speaker recognition is an important topic to be performed by a computer system. In this paper, an expert speaker recognition system based on optimum wavelet packet entropy is proposed for speaker recognition by using real speech/voice signal. This study contains both the combination of the new feature extraction and classification approach by using optimum wavelet packet entropy parameter values. These optimum wavelet packet entropy values are obtained from measured real English language speech/voice signal waveforms using speech experimental set. A genetic-wavelet packet-neural network (GWPNN) model is developed in this study. GWPNN includes three layers which are genetic algorithm, wavelet packet and multi-layer perception. The genetic algorithm layer of GWPNN is used for selecting the feature extraction method and obtaining the optimum wavelet entropy parameter values. In this study, one of the four different feature extraction methods is selected by using genetic algorithm. Alternative feature extraction methods are wavelet packet decomposition, wavelet packet decomposition – short-time Fourier transform, wavelet packet decomposition – Born–Jordan time–frequency representation, wavelet packet decomposition – Choi–Williams time–frequency representation. The wavelet packet layer is used for optimum feature extraction in the time–frequency domain and is composed of wavelet packet decomposition and wavelet packet entropies. The multi-layer perceptron of GWPNN, which is a feed-forward neural network, is used for evaluating the fitness function of the genetic algorithm and for classification speakers. The performance of the developed system has been evaluated by using noisy English speech/voice signals. The test results showed that this system was effective in detecting real speech signals. The correct classification rate was about 85% for speaker classification.     

Anisotropic Probabilistic Neural Network for Image Interpolation

This study proposes a novel image interpolation method based on an anisotropic probabilistic neural network (APNN). The proposed method uses an anisotropic Gaussian kernel to improve image interpolation, which causes blurred edges. The objective of this anisotropic Gaussian kernel-based probabilistic neural network is to provide high adaptivity of smoothness/sharpness during image/video interpolation. This APNN interpolation method adjusts the smoothing parameters for varied smooth/edge regions, and considers edge direction. This APNN uses a single neuron to estimate sharpness/smoothness. The proposed method achieves better sharpness enhancement at edge regions, and reveals the noise reduction at smooth region. This study also uses interpolating a slanted-edge image to reveal blurring and blocking effects. Finally, this study compares the performance of these proposed methods with other image interpolation methods.     

Fault diagnosis of rolling bearing based on back propagation neural network optimized by cuckoo search algorithm

In order to improve the accuracy of rolling bearing fault diagnosis in mechanical equipment, a new fault diagnosis method based on back propagation neural network optimized by cuckoo search algorithm is proposed. This method use the global search ability of the cuckoo search algorithm to constantly search for the best weights and thresholds, and then give it to the back propagation neural network. In this paper, wavelet packet decomposition is used for feature extraction of vibration signals. The energy values of different frequency bands are obtained through wavelet packet decomposition, and they are input as feature vectors into optimized back propagation neural network to identify different fault types of rolling bearings. Through the three sets of simulation comparison experiments of Matlab, the experimental results show that, Under the same conditions, compared with the other five models, the proposed back propagation neural network optimized by cuckoo search algorithm has the least number of training iterations and the highest diagnostic accuracy rate. And in the complex classification experiment with the same fault location but different bearing diameters, the fault recognition correct rate of the back propagation neural network optimized by cuckoo search algorithm is 96.25%.

     

The construction of wavelet network for speech signal processing

Wavelet decomposition reconstructs a signal by a series of scaled and translated wavelets. Incorporating discrete wavelet decomposition theory with neural network techniques, wavelet networks have recently emerged as a powerful tool for many applications in the field of signal processing, such as data compression and function approximation. In this paper, four contributions are claimed: (1) From the point of view of machine learning, we analyse and construct wavelet network to achieve the compact representation of a signal. (2) A new algorithm of constructing wavelet network is proposed. The orthogonal least square (OLS) is employed to prune the wavelet network. (3) Our experiments on speech signal processing results show that the wavelet network pruned by OLS achieves the best approximation and prediction capabilities among the representative speech processing techniques. (4) Our proposed methodology has been successfully applied to speech synthesis for a talking head to read web texts.     

引入神经网络中间神经元的快速小波图像压缩

目的针对自组织特征映射(SOFM)算法会出现严重的分块现象和快速小波变换在高压缩比的情况下图像恢复质量差的问题,提出引入神经网络中间神经元(relay neurons)的RSOFM-C矢量量化算法。方法引入了中间神经元的概念,使用中间神经元有效解决了码字利用不均匀的问题,并在神经网络中间层给出了欧氏距离不等式判据,排除不满足失真测度的神经元,减少重复计算,加快学习速度。根据差分脉冲编码调制(DPCM)中的差值信号编码原理将RSOFM-C算法与快速小波变换结合,使用RSOFM-C算法对由快速小波变换得到的图像低频信号进一步压缩。结果在仿真实验中,将本文算法与同类压缩方法进行对比,当压缩比为52%时,本文算法的峰值信噪比(PSNR)达到了39.28 d B,远远高于其他方法。结果表明,本文的压缩算法消除了分块现象,并且在保证高压缩比的同时获得高质量的重构图像。结论实验结果表明,本文提出的引入了中间神经元的快速小波压缩方法,具有高压缩比、高保真、速度快等优点,可以高效地压缩图像。