改进胶囊网络优化分层卷积的亚健康识别算法

针对传统卷积神经网络(CNN)为获得高准确率不断堆叠卷积层、池化层致使模型结构复杂、训练时间长且数据处理方式单一的问题,提出改进胶囊网络优化分层卷积的亚健康识别算法。首先,对原始振动数据进行小波降噪和小波包降噪两种数据处理,更好地保留原始信号中对亚健康识别有用的信息;其次,CNN采用分层卷积的思想,并行3个不同尺度的卷积核,多角度地进行特征提取;最后,将卷积核提取的特征输入到剪枝策略的胶囊网络中进行亚健康识别,改进的胶囊网络在保证准确率的同时加快亚健康识别时间,解决CNN结构过于复杂以及识别效果不佳的问题。实验结果表明,提出算法识别准确率高且识别时间较少。     

Non-local duplicate pooling network for salient object detection

Many existing salient object detection methods are dedicated to fusing features from different levels of a pre-trained convolutional neural network (CNN). However, these methods can easily lead to internal discontinuities within the salient objects because of unreasonable feature fusion strategies and short-range dependencies resulting from common convolution and pooling operations. In this paper, we propose a novel non-local duplicate pooling (NLDP) network to overcome these internal discontinuities. NLDP begins by removing the first few convolutional layers of a classic CNN, which have small receptive fields and require large amounts of calculation. A novel duplicate pooling module (DPM) is then used to generate richer and more detailed saliency maps. This is achieved by constructing a double-pathway that can integrating partial feature maps. Within the DPM, a non-local module (NLM) is used to obtain long-range dependencies. This enhances the internal continuities between the saliency maps. Comprehensive experiments conducted on six benchmark datasets have confirmed the increased effectiveness and detection speed of our method in relation to other salient object detection methods.

     

基于多尺度分块卷积神经网络的图像目标识别算法

针对图像在平移、旋转或局部形变等复杂情况下的识别问题,提出一种基于非监督预训练和多尺度分块的卷积神经网络(CNN)目标识别算法。算法首先利用不含标签的图像训练一个稀疏自动编码器,得到符合数据集特性、有较好初始值的滤波器集合。为了增强鲁棒性,同时减小下采样对特征提取的影响,提出一种多通路结构的卷积神经网络,对输入图像进行多尺度分块形成多个通路,每个通路与相应尺寸的滤波器卷积,不同通路的特征经过局部对比度标准化和下采样后在全连接层进行融合,从而形成最终用于图像分类的特征,将特征输入分类器完成图像目标识别。仿真实验中,所提算法对STL-10数据集和遥感飞机图像的识别率较传统的CNN均有提高,并对图像各种形变具有较好的鲁棒性。     

结合余弦相关性的卷积网络识别汉字的方法

为了提高卷积神经网络（Convolution Neural Network,CNN）的识别率,增强卷积网络的特征提取能力,使其在模糊、光照不均等恶劣条件下能够有更好的识别效果,因此提出将余弦相关性加入神经卷积网络作为相似度度量的方法。较传统神经卷积网络相比较,有着更强的模式检测能力、更快的收敛速度以及更高的准确率的优点。在卷积神经网络的卷积层加入余弦相似性度量,最后通过对比传统神经卷积网络方法和余弦相关性神经卷积网络在脱机手写汉字的识别实验,在进行20次实验后,得出了在相同训练参数以及相同层数的卷积神经网络上,基于余弦相关性的神经卷积网络在手写汉字数据集上的准确率比传统的神经卷积网络的识别率平均提高了2.01%,并且有着更快的收敛速度。最后通过与现今流行的算法在MNIST数据集上的实验进行准确度、损失函数、时间复杂度的比较,得出结合余弦的卷积神经网络在准确度和损失函数上有一定的优势性,在时间复杂度上还需进一步提高。     

基于中间层监督卷积神经网络的图像超分辨率重建

目的 基于学习的图像超分辨率重建方法已成为近年来图像超分辨率重建研究的热点。针对基于卷积神经网络的图像超分辨率重建（SRCNN）方法网络层少、感受野小、泛化能力差等缺陷,提出了基于中间层监督卷积神经网络的图像超分辨率重建方法,以进一步提高图像重建的质量。方法 设计了具有中间层监督的卷积神经网络结构,该网络共有16层卷积层,其中第7层为中间监督层;定义了监督层误差函数和重建误差函数,用于改善深层卷积神经网络梯度消失现象。训练网络时包括图像预处理、特征提取和图像重建3个步骤,采用不同尺度因子（2、3、4）模糊的低分辨率图像交叉训练网络,以适应对不同模糊程度的图像重建;使用卷积操作提取图像特征时将参数pad设置为1,提高了对图像和特征图的边缘信息利用;利用残差学习完成高分辨率图像重建。结果 在Set5和Set14数据集上进行了实验,并和双三次插值、A+、SelfEx和SRCNN等方法的结果进行比较。在主观视觉评价方面,本文方法重建图像的清晰度和边缘锐度更好。客观评价方面,本文方法的峰值信噪比（PSNR）平均分别提高了2.26 dB、0.28 dB、0.28 dB和0.15 dB,使用训练好的网络模型重建图像耗用的时间不及SRCNN方法的一半。结论 实验结果表明,本文方法获得了更好的主观视觉评价和客观量化评价,提升了图像超分辨率重建质量,泛化能力好,而且图像重建过程耗时更短,可用于自然场景图像的超分辨率重建。     

Genetic design of biologically inspired receptive fields for neural pattern recognition

This paper proposes a new method for the design, through simulated evolution, of biologically inspired receptive fields in feedforward neural networks (NNs). The method is intended to enhance pattern recognition performance by creating new neural architectures specifically tuned for a particular pattern recognition problem. It proposes a combined neural architecture composed of two networks in cascade: a feature extraction network (FEN) followed by a neural classifier. The FEN is composed of several layers with receptive fields constructed by additive superposition of excitatory and inhibitory fields. A genetic algorithm (GA) is used to select receptive field parameters to improve classification performance. The parameters are receptive field size, orientation, and bias as well as the number of different receptive fields in each layer. Based on a random initial population where each individual represents a different neural architecture, the GA creates new enhanced individuals. The method is applied to handwritten digit classification and face recognition. In both problems, results show strong dependency between NN classification performance and receptive field architecture. GA selected parameters of the receptive fields produced improvements in the classification performance on the test set up to 90.8% for the problem of handwritten digit classification and up to 84.2% for the face recognition problem. On the same test sets, results were compared advantageously to standard feedforward multilayer perceptron (MLP) NNs where receptive fields are not explicitly defined. The MLP reached a maximum classification performance of 84.9% and 77.5% in both problems, respectively.     

基于改进CNN的年龄和性别识别

人脸图像的年龄和性别识别是人脸分析的重要任务,在真实多变场景下完成识别依然面临挑战。改进深度卷积神经网络（Convolutional Neural Network,CNN）,将首层大尺寸卷积核替换为级联3[×]3卷积核;采用跨连卷积层融合中层和高层抽象特征;加入Batch Normalization（BN）层,设置较高的学习率和较小的Dropout比率;采用1[×]1卷积核与全局平均池化（Global Average Pooling）取代全连接层。实验表明,所提方法与主流的年龄性别识别方法比较具有较好的识别率,在Adience数据集上,年龄识别精度达到89.8%,性别识别精度达到93.3%。     

基于卷积神经网络和Transformer的手写体英文文本识别

手写体文本识别技术可以将手写文档转录成可编辑的数字文档。但由于手写的书写风格迥异、文档结构千变万化和字符分割识别精度不高等问题,基于神经网络的手写体英文文本识别仍面临着许多挑战。针对上述问题,提出基于卷积神经网络（CNN）和Transformer的手写体英文文本识别模型。首先利用CNN从输入图像中提取特征,而后将特征输入到Transformer编码器中得到特征序列每一帧的预测,最后经过链接时序分类（CTC）解码器获得最终的预测结果。在公开的IAM（Institut für Angewandte Mathematik）手写体英文单词数据集上进行了大量的实验结果表明,该模型获得了3.60%的字符错误率（CER）和12.70%的单词错误率（WER）,验证了所提模型的可行性。     

基于二维主成分分析与卷积神经网络的手写体汉字识别

随着计算能力的飞速增长、训练数据的不断积累以及非线性激活函数的不断完善,卷积神经网络（CNN）在手写体汉字识别中表现出较好的识别性能。针对CNN识别手写体汉字识别速度慢的问题,将二维主成分分析（2DPCA）与CNN相结合识别手写体汉字。首先,利用2DPCA提取手写体汉字的投影特征向量;然后,将得到的投影特征向量组成特征矩阵;其次,用组成的特征矩阵作为CNN的输入;最后,用Softmax函数进行分类。与基于AlexNet的CNN模型相比,所提方法的运行时间降低了78%,与基于ACNN与DCNN的模型相比,所提方法的运行时间分别降低了80%与73%。实验结果表明,该方法在不降低识别精度的同时,可以减少识别手写体汉字的运行时间。     

多重水印快速加密技术在图象深度传感器中的应用

本文研究了金融电子票据中高效率的快速多重数字水印加密在图象深度传感器中的应用方法,针对票据中的数字、签名等关键内容容易被篡改的问题,针对关键区域进行卷积神经网络的识别和水印加密。首先,利用卷积神经网络识别票据中的关键信息区域,以减少水印加密的运算数据量,提高金融票据自动处理效率。在传统的网络结构中,由于CNN的卷积池化操作,使得粗粒度和边缘信息丢失,CNN网络中最顶层的信息维度偏低,易导致过拟合。针对上述问题,本文提出利用票据图及其差分特征,构建适合CNN网络的多通道图像输入特征,充分挖掘图像内在特征;然后进一步改进传统的CNN网络结构,把所有卷积层的输出连接为一层,构成包含各层信息的融合特征,输入网络的全连接层进行分类识别。实验结果表明,改进后的CNN识别算法,相较传动CNN、DNN等算法,其性能均有明显提升,能够更加高效的进行多个关键区域的内容识别,从而高效的进行多重数字水印的加密,提高金融票据处理的安全性和运算效率。     

Recognizing arabic handwritten characters using deep learning and genetic algorithms

Automated techniques for Arabic content recognition are at a beginning period contrasted with their partners for the Latin and Chinese contents recognition. There is a bulk of handwritten Arabic archives available in libraries, data centers, historical centers, and workplaces. Digitization of these documents facilitates (1) to preserve and transfer the country’s history electronically, (2) to save the physical storage space, (3) to proper handling of the documents, and (4) to enhance the retrieval of information through the Internet and other mediums. Arabic handwritten character recognition (AHCR) systems face several challenges including the unlimited variations in human handwriting and the leakage of large and public databases. In the current study, the segmentation and recognition phases are addressed. The text segmentation challenges and a set of solutions for each challenge are presented. The convolutional neural network (CNN), deep learning approach, is used in the recognition phase. The usage of CNN leads to significant improvements across different machine learning classification algorithms. It facilitates the automatic feature extraction of images. 14 different native CNN architectures are proposed after a set of try-and-error trials. They are trained and tested on the HMBD database that contains 54,115 of the handwritten Arabic characters. Experiments are performed on the native CNN architectures and the best-reported testing accuracy is 91.96%. A transfer learning (TF) and genetic algorithm (GA) approach named “HMB-AHCR-DLGA” is suggested to optimize the training parameters and hyperparameters in the recognition phase. The pre-trained CNN models (VGG16, VGG19, and MobileNetV2) are used in the later approach. Five optimization experiments are performed and the best combinations are reported. The highest reported testing accuracy is 92.88%.

     

AKSNet: A novel convolutional neural network with adaptive kernel width and sparse regularization for machinery fault diagnosis

Convolutional kernels have significant affections on feature learning of convolutional neural network (CNN). However, it is still a challenging problem to determine appropriate kernel width. Moreover, some features learned by convolutional layers are still redundant and noisy. Thus, adaptive selection of kernel width and feature selection of feature maps are key techniques to improve feature learning performance of CNNs. In this paper, a new deep neural network (DNN) model, adaptive kernel sparse network (AKSNet) is proposed to extract multi-scale fault features from one-dimensional (1-D) vibration signals. Firstly, an adaptive kernel selection method is developed, where multiple branches with different kernels are used to extract multi-scale features from vibration signals. Channel-wise attention is developed to fuse features generated by these kernels to obtain different informative scales. Secondly, a spatial attention is used for dynamic receptive field to focus on salient region of feature maps. Thirdly, a sparse regularization layer is embedded in the deep network to further filter noise and highlight impaction of the feature maps. Finally, two cases are adopted to verify effectiveness of AKSNet-based feature learning for bearing fault diagnosis. Experimental results show that AKSNet can effectively extract features from multi-channel vibration signals and then improves fault diagnosis performance of the classifier significantly. AKSNet shows better recognition performance in comparison with that of shallow neural networks and other typical DNNs.     

手写体数字识别与认证的小波特征提取

本文提出了基于Kirsch边缘增强的二维小波特征与二维复小波特征的提取技术。这两类特征与几何特征融合识别手写体数字。此外，对所提取的小波特征提取方法的优点进行了讨论。最后进行的手写体数字识别与认证实验表明，这两类混合特征的集合能获得很好的识别与认证性能。     

手写体汉字识别中小波分形分解特征的研究

研究了手写体汉字识别中的一种新的特征提取方法——小波分形分解特征。对手写汉字分别采用小波和分形的方法提取其结构特征和统计特征,并将提取的结构特征和统计特征组合后作为识别器的输入进行识别。实验结果表明,对训练样本可以达到98．71％识别率,对测试样本可以达到91．37％识别率。     

A Pyramidal Neural Network For Visual Pattern Recognition

In this paper, we propose a new neural architecture for classification of visual patterns that is motivated by the two concepts of image pyramids and local receptive fields. The new architecture, called pyramidal neural network (PyraNet), has a hierarchical structure with two types of processing layers: Pyramidal layers and one-dimensional (1-D) layers. In the new network, nonlinear two-dimensional (2-D) neurons are trained to perform both image feature extraction and dimensionality reduction. We present and analyze five training methods for PyraNet [gradient descent (GD), gradient descent with momentum, resilient backpropagation (RPROP), Polak-Ribiere conjugate gradient (CG), and Levenberg-Marquadrt (LM)] and two choices of error functions [mean-square-error (mse) and cross-entropy (CE)]. In this paper, we apply PyraNet to determine gender from a facial image, and compare its performance on the standard facial recognition technology (FERET) database with three classifiers: The convolutional neural network (NN), the k-nearest neighbor (k-NN), and the support vector machine (SVM)     

基于多流CNN-LSTM网络的群体情绪识别

群体情绪识别是人机交互领域的前言课题,针对群体情绪识别准确率的问题,结合卷积神经网络（CNN）与长短期记忆网络（LSTM）,提出一种多流CNN-LSTM网络模型学习群体情绪的静态和动态特征。以视频序列的原始图像、视觉显著图形和叠加的光流图像分别作为三个通道的输入,利用CNN网络对空间特征和局部运动特征进行分析,得到的特征图直接输入LSTM网络,进行全局运动特征的学习。最后连接Softmax分类器,对三个通道的Softmax输出进行加权融合,得到分类结果。实验结果表明,本文模型可有效地识别4种典型的群体情绪,且识别率高于已有算法,准确度（ACC）和宏平均精度（MAP）分别最高可达82.6%、84.1%。     

Writer adaptation via deeply learned features for online Chinese handwriting recognition

This paper proposes a novel framework of writer adaptation based on deeply learned features for online handwritten Chinese character recognition. Our motivation is to further boost the state-of-the-art deep learning-based recognizer by using writer adaptation techniques. First, to perform an effective and flexible writer adaptation, we propose a tandem architecture design for the feature extraction and classification. Specifically, a deep neural network (DNN) or convolutional neural network (CNN) is adopted to extract the deeply learned features which are used to build a discriminatively trained prototype-based classifier initialized by Linde–Buzo–Gray clustering techniques. In this way, the feature extractor can fully utilize the useful information of a DNN or CNN. Meanwhile, the prototype-based classifier could be designed more compact and efficient as a practical solution. Second, the writer adaption is performed via a linear transformation of the deeply learned features which is optimized with a sample separation margin-based minimum classification error criterion. Furthermore, we improve the generalization capability of the previously proposed discriminative linear regression approach for writer adaptation by using the linear interpolation of two transformations and adaptation data perturbation. The experiments on the tasks of both the CASIA-OLHWDB benchmark and an in-house corpus with a vocabulary of 20,936 characters demonstrate the effectiveness of our proposed approach.     

基于EEG和DE-CNN-GRU的情绪识别

近年,情绪识别研究已经不再局限于面部和语音识别,基于脑电等生理信号的情绪识别日趋火热.但由于特征信息提取不完整或者分类模型不适应等问题,使得情绪识别分类效果不佳.基于此,本文提出一种微分熵(DE)、卷积神经网络(CNN)和门控循环单元(GRU)结合的混合模型(DE-CNN-GRU)进行基于脑电的情绪识别研究.将预处理后的脑电信号分成5个频带,分别提取它们的DE特征作为初步特征,输入到CNN-GRU模型中进行深度特征提取,并结合Softmax进行分类.在SEED数据集上进行验证,该混合模型得到的平均准确率比单独使用CNN或GRU算法的平均准确率分别高出5.57%与13.82%.     

A comprehensive study of hybrid neural network hidden Markov model for offline handwritten Chinese text recognition

This paper proposes an effective segmentation-free approach using a hybrid neural network hidden Markov model (NN-HMM) for offline handwritten Chinese text recognition (HCTR). In the general Bayesian framework, the handwritten Chinese text line is sequentially modeled by HMMs with each representing one character class, while the NN-based classifier is adopted to calculate the posterior probability of all HMM states. The key issues in feature extraction, character modeling, and language modeling are comprehensively investigated to show the effectiveness of NN-HMM framework for offline HCTR. First, a conventional deep neural network (DNN) architecture is studied with a well-designed feature extractor. As for the training procedure, the label refinement using forced alignment and the sequence training can yield significant gains on top of the frame-level cross-entropy criterion. Second, a deep convolutional neural network (DCNN) with automatically learned discriminative features demonstrates its superiority to DNN in the HMM framework. Moreover, to solve the challenging problem of distinguishing quite confusing classes due to the large vocabulary of Chinese characters, NN-based classifier should output 19900 HMM states as the classification units via a high-resolution modeling within each character. On the ICDAR 2013 competition task of CASIA-HWDB database, DNN-HMM yields a promising character error rate (CER) of 5.24% by making a good trade-off between the computational complexity and recognition accuracy. To the best of our knowledge, DCNN-HMM can achieve a best published CER of 3.53%.     

基于多重规则和路径评价的在线中英文手写识别方法

手写文本识别方法主要应用于文本输入技术,对人机交互领域的发展起关键作用。针对多数在线输入法无法识别中英文混合手写识别的问题,提出一种在线中英文混合手写文本识别方法。通过对文本笔画进行基于水平相对位置、垂直重叠率、面积重叠率规则的整合以及连笔切分,得到一系列字符片段,同时利用笔画个数、宽高比、中心偏离、平滑度等几何特征和识别置信度,对字符片段进行中英文分类。在此基础上,根据分类结果并结合自然语言模型的路径评价及动态规划搜索算法,分别对候选的中、英文字符片段进行合并处理,得到待识别的中、英文字符序列,并将其分别送入卷积神经网络的中、英文识别模型中,得到手写文本识别结果。实验结果表明,在线手写中英文混合文本识别正确率达93.67%,不仅能切分在线手写中文文本行,而且对包含字符连笔的在线手写中英文文本行也有较好的切分效果。