应用一种多核稀疏表示模型实现掌纹分类

与稀疏表示(SR)模型相比,基于单个核函数的SR(KSR)模型可以有效减少数据维数、降低学习模型的计算复杂度并提高特征分类精度;但这种模型对核函数及其参数的选择通常不能包含恰当的、完整的分类信息。为了满足更高的特征分类精度需求,提出了一种基于多个核函数的SR(M-KSR)模型及其快速稀疏优化方法,并将其应用于掌纹图像的分类。测试结果证明了基于M-KSR模型的掌纹分类方法的有效性和实用性。     

基于多级特征融合的体素三维目标检测网络

目的 为精确分析点云场景中待测目标的位置和类别信息,提出一种基于多级特征融合的体素三维目标检测网络。方法 以2阶段检测算法Voxel?RCNN作为基线模型,在检测一阶段,增加稀疏特征残差密集融合模块,由浅入深地对逐级特征进行传播和复用,实现三维特征充分的交互融合。在二维主干模块中增加残差轻量化高效通道注意力机制,显式增强通道特征。提出多级特征及多尺度核自适应融合模块,自适应地提取各级特征的关系权重,以加权方式实现特征的强融合。在检测二阶段,设计三重特征融合策略,基于曼哈顿距离搜索算法聚合邻域特征,并嵌入深度融合模块和CTFFM融合模块提升格点特征质量。结果 实验于自动驾驶数据集KITTI中进行模拟测试,相较于基线网络,在3种难度等级下,一阶段检测模型的行人3D平均精度提升了3.97%,二阶段检测模型的骑行者3D平均精度提升了3.37%。结论 结果证明文中方法能够显著提升目标检测性能,且各模块具有较好的移植性,可灵活嵌入到体素类三维检测模型中,带来相应的效果提升。     

Semi-GSGCN: Social Robot Detection Research with Graph Neural Network

Malicious social robots are the disseminators of malicious information on social networks, which seriously affect information security and network environments. Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks. Supervised classification based on manual feature extraction has been widely used in social robot detection. However, these methods not only involve the privacy of users but also ignore hidden feature information, especially the graph feature, and the label utilization rate of semi-supervised algorithms is low. Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods, in this paper a robot detection scheme based on weighted network topology is proposed, which introduces an improved network representation learning algorithm to extract the local structure features of the network, and combined with the graph convolution network (GCN) algorithm based on the graph filter, to obtain the global structure features of the network. An end-to-end semi-supervised combination model (Semi-GSGCN) is established to detect malicious social robots. Experiments on a social network dataset (cresci-rtbust-2019) show that the proposed method has high versatility and effectiveness in detecting social robots. In addition, this method has a stronger insight into robots in social networks than other methods.     

基于核竞争学习算法的图像特征提取

利用核函数学习可有效解决图像特征线性不可分的特性,结合稀疏表示算法的优势,提出了一种新的图像特征提取方法。采用基于竞争学习规则的独立分量分析法对图像进行稀疏表示,该算法可提取数据的高维特征,且不需要优化高阶的非线性函数和进行稀疏密度估计,因而有较快的收敛速度。与仅使用基于竞争学习的独立分量分析法相比,在PolyU数据库上的实验结果表明,采用基于核函数学习和稀疏表示相结合的方法所提取的数据特征有利于提高特征分类精度。     

Virtual images inspired consolidate collaborative representation-based classification method for face recognition

Abstract

The collaborative representation-based classification method performs well in the field of classification of high-dimensional images such as face recognition. It utilizes training samples from all classes to represent a test sample and assigns a class label to the test sample using the representation residuals. However, this method still suffers from the problem that limited number of training sample influences the classification accuracy when applied to image classification. In this paper, we propose a modified collaborative representation-based classification method (MCRC), which exploits novel virtual images and can obtain high classification accuracy. The procedure to produce virtual images is very simple but the use of them can bring surprising performance improvement. The virtual images can sufficiently denote the features of original face images in some case. Extensive experimental results doubtlessly demonstrate that the proposed method can effectively improve the classification accuracy. This is mainly attributed to the integration of the collaborative representation and the proposed feature-information dominated virtual images.     

基于KSLPP与RWKNN的旋转机械故障诊断

针对旋转机械高维故障特征集识别精度低的问题,提出基于核监督局部保留投影（Kernel Supervised Locality Preserving Projection, KSLPP）与ReliefF特征加权的K近邻（ReliefF Weighted K-Nearest Neighbor, RWKNN）分类器相结合的维数约简故障诊断方法。该方法首先应用KSLPP提取故障特征集中的非线性信息,同时在降维投影过程中充分利用类别信息,使降维后最小化类内散度,最大化类间分离度;随后,将降维后得到的低维敏感特征集输入RWKNN进行模式识别,RWKNN能够突出不同特征对分类的贡献率,强化敏感特征,弱化不相关特征,提升了分类精度和鲁棒性。最后,通过典型转子实验台的故障特征集验证了该方法的有效性。     

基于敏感特征选择与流形学习维数约简的故障诊断

针对故障诊断中特征集包含非敏感特征和维数过高的问题,提出基于特征选择(Feature selection, FS)与流形学习维数约简的故障诊断方法。提出了一种改进的核空间距离测度特征选择方法(Improved kernel distance measurement feature selection, IKMD-FS),在核空间中计算样本类间距离和类内散度,优选出使样本类间距大、类内散度小的特征,并根据特征的敏感程度对特征进行加权。通过线性局部切空间排列算法(Linear local tangent space alignment, LLTSA)对由敏感特征组成的特征子集进行特征融合,提取出对故障分类更加敏感的融合特征,并输入加权k最近邻分类器(Weighted k nearest neighbor classifier, WKNNC)进行故障识别。WKNNC具有比k最近邻分类器(k nearest neighbor classifier, KNNC)更加稳定的识别精度。最后,通过滚动轴承故障模拟实验验证了本文方法的有效性。     

Weighted Sparse Image Classification Based on Low Rank Representation

The conventional sparse representation-based image classification usually codes the samples independently, which will ignore the correlation information existed in the data. Hence, if we can explore the correlation information hidden in the data, the classification result will be improved significantly. To this end, in this paper, a novel weighted supervised spare coding method is proposed to address the image classification problem. The proposed method firstly explores the structural information sufficiently hidden in the data based on the low rank representation. And then, it introduced the extracted structural information to a novel weighted sparse representation model to code the samples in a supervised way. Experimental results show that the proposed method is superiority to many conventional image classification methods.     

An improved SRC method based on virtual samples for face recognition

The sparse representation classifier (SRC) performs classification by evaluating which class leads to the minimum representation error. However, in real world, the number of available training samples is limited due to noise interference, training samples cannot accurately represent the test sample linearly. Therefore, in this paper, we first produce virtual samples by exploiting original training samples at the aim of increasing the number of training samples. Then, we take the intra-class difference as data representation of partial noise, and utilize the intra-class differences and training samples simultaneously to represent the test sample in a linear way according to the theory of SRC algorithm. Using weighted score level fusion, the respective representation scores of the virtual samples and the original training samples are fused together to obtain the final classification results. The experimental results on multiple face databases show that our proposed method has a very satisfactory classification performance.     

TM和SAR遥感图象特征层融合分类方法的研究

针对空间遥感ＴＭ图象和ＳＡＲ图象信息的特征层融合应用于地物分类,提出了一种结合Ｍａｒｋｏｖ随机场和ＢＰ神经网络模型的多源遥感图象迭代分类方法。该分类方法与现有的基于Ｍａｒｋｏｖ模型的分类器相比具有无须假设条件概率密度函数模型的优点;与ＢＰ神经网络分类器相比,由于其考虑了类别标号的空间相关性,提高了分类精度;有别于传统的上下文分类器：它是通过迭代过程中来实现分类的,在考虑了类别标号的空间相关性的同时     

Multi-task Joint Sparse Representation Classification Based on Fisher Discrimination Dictionary Learning

Recently, sparse representation classification (SRC) and fisher discrimination dictionary learning (FDDL) methods have emerged as important methods for vehicle classification. In this paper, inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection, we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors. To improve the classification accuracy in complex scenes, we develop a new method, called multi-task joint sparse representation classification based on fisher discrimination dictionary learning, for vehicle classification. In our proposed method, the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients (MFCC). Moreover, we extend our model to handle sparse environmental noise. We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.     

Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the resolution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images; and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.     

Modelling of spatial causality among distinctive properties of an image using conditional random field for image classification

In this paper, we proposed an ordered patch-based method using conditional random field (CRF) in order to encode local properties and their spatial relationship in the images to address texture classification, face recognition and scene classification problems. Typical image classification approaches classify images without considering spatial causality among distinctive properties of an image to represent it in the feature space. In this method first, each image is encoded as a sequence of ordered patches including local properties. Second, the sequence of these ordered patches is modelled as a probabilistic feature vector using CRF to model spatial relationship of these local properties; and finally, image classification is performed on such probabilistic image representation. Experimental results on several standard image datasets indicate that the proposed method outperforms some of existing image classification methods.     

A Two-Stage Vehicle Type Recognition Method Combining the Most Effective Gabor Features

Vehicle type recognition (VTR) is an important research topic due to its significance in intelligent transportation systems. However, recognizing vehicle type on the real-world images is challenging due to the illumination change, partial occlusion under real traffic environment. These difficulties limit the performance of current stateof-art methods, which are typically based on single-stage classification without considering feature availability. To address such difficulties, this paper proposes a twostage vehicle type recognition method combining the most effective Gabor features. The first stage leverages edge features to classify vehicles by size into big or small via a similarity k-nearest neighbor classifier (SKNNC). Further the more specific vehicle type such as bus, truck, sedan or van is recognized by the second stage classification, which leverages the most effective Gabor features extracted by a set of Gabor wavelet kernels on the partitioned key patches via a kernel sparse representation-based classifier (KSRC). A verification and correction step based on minimum residual analysis is proposed to enhance the reliability of the VTR. To improve VTR efficiency, the most effective Gabor features are selected through gray relational analysis that leverages the correlation between Gabor feature image and the original image. Experimental results demonstrate that the proposed method not only improves the accuracy of VTR but also enhances the recognition robustness to illumination change and partial occlusion.     

A novel region-based multimodal image fusion technique using improved dictionary learning

Recently, the sparse representation (SR) based algorithms have gained much attention from the researchers in the area of image fusion (IF). The building of a compact discriminative dictionary plays a vital role in the sparse-based IF techniques. In this context, an efficient multimodal IF method based on improved dictionary learning is investigated. The key contributions of this paper are: (a) An improved KSVD algorithm is suggested for the dictionary learning process, (b) to reduce the computational time, only the informative patches are selected using energy feature, and (c) a novel region-based fusion scheme is suggested for the first time for the problem on hand. The suggested technique is tested with a number of multimodal images from Harvard Medical School brain database. The results are compared with state-of-the-art multiscale transform-based methods and modified SR-based methods. Unlike earlier methods, our proposed technique generates an adaptive dictionary through selection of informative patches only. This results in a compact dictionary with improved computational efficiency. The experimental results reveal that our approach outperforms other methods. The potential application of the suggested method could be in pathological images for follow-up study and better treatment planning.     

基于多分辨率时频特征融合的声学场景分类

声学场景分类是计算机听觉中最难的任务之一,在单一特征条件下采用基本的卷积神经网络相对于传统的分类方法精度已经有所提升,但是效果依然不够理想。针对这一问题,在卷积神经网络框架下,提出了一种基于时频特征融合的声学场景分类方案。在分类模型构建方面,提出一种多分辨率卷积池化方案,构造多分辨率卷积神经网络,以更好地适应提取特征的时频结构;在特征选取方面,融合低层次包络特征对数——Mel子带能量和高层次结构特征——非负矩阵分解系数矩阵,把两种二维特征堆叠为三维特征送入分类模型。在2017年和2018年声学场景分类和事件检测挑战赛的开发数据集上进行了训练和测试。实验结果表明,文中提出方案比基线系统的分类精度分别提高7.5%和10.3%,可有效改善分类效果。     

Category-specific scene categorization

Scene categorization with category-specific visual-word construction and image representation is proposed in this study. The proposed scene categorization has effective discriminative ability and class extendibility. The reasons are listed as follows. First, since the visual-word construction and image representation are category-specific, the corresponding learning model for classification has substantial discriminating power. Second, since the visual-word construction and image representation are category-specific, image features related to the original classes need not be recreated when new classes are added, which minimizes reconstruction overhead. Experimental results confirm that the accuracy of the proposed method is superior to existing methods with single-type features both in single-scale and in multi-scale versions.     

基于卷积神经网络模型的遥感图像分类

研究了遥感图像的分类,针对遥感图像的支持向量机(SVM)等浅层结构分类模型特征提取困难、分类精度不理想等问题,设计了一种卷积神经网络(CNN)模型,该模型包含输入层、卷积层、全连接层以及输出层,采用Soft Max分类器进行分类。选取2010年6月6日Landsat TM5富锦市遥感图像为数据源进行了分类实验,实验表明该模型采用多层卷积池化层能够有效地提取非线性、不变的地物特征,有利于图像分类和目标检测。针对所选取的影像,该模型分类精度达到94.57%,比支持向量机分类精度提高了5%,在遥感图像分类中具有更大的优势。     

Image fusion based on wavelet transform and gray-level features

Image fusion makes the fused image more reliable and intelligible, and more suitable for human vision and computer detection, classification, recognition and understanding. This paper proposes a pixel-level image fusion method for merging two source images of the same scene using wavelet transform and gray-level features (GLF). First, a three-level discrete two-dimensional wavelet transform is used to decompose the two source images into low-frequency image components and horizontal, vertical, and diagonal high-frequency components. Then, the spatial frequency correlation coefficient is used to determine the pixel fusion rule to apply to each of the low-frequency images, and the correlation coefficient of the GLF is used to determine the pixel fusion rule to apply to each of the high-frequency images. Finally, the fused image is reconstructed using inverse wavelet transform. The results of the experiments conducted indicate that the proposed method is more effective than relevant conventional methods.     

Traffic Sign Recognition Method Integrating Multi-Layer Features and Kernel Extreme Learning Machine Classifier

Traffic sign recognition (TSR), as a critical task to automated driving and driver assistance systems, is challenging due to the color fading, motion blur, and occlusion. Traditional methods based on convolutional neural network (CNN) only use an end-layer feature as the input to TSR that requires massive data for network training. The computation-intensive network training process results in an inaccurate or delayed classification. Thereby, the current state-of-the-art methods have limited applications. This paper proposes a new TSR method integrating multi-layer feature and kernel extreme learning machine (ELM) classifier. The proposed method applies CNN to extract the multi-layer features of traffic signs, which can present sufficient details and semantically abstract information of multi-layer feature maps. The extraction of multi-scale features of traffic signs is effective against object scale variation by applying a new multi-scale pooling operation. Further, the extracted features are combined into a multi-scale multi-attribute vector, which can enhance the feature presentation ability for TSR. To efficiently handle nonlinear sampling problems in TSR, the kernel ELM classifier is adopted for efficient TSR. The kernel ELM has a more powerful function approximation capability, which can achieve an optimal and generalized solution for multiclass TSR. Experimental results demonstrate that the proposed method can improve the recognition accuracy, efficiency, and adaptivity to complex travel environments in TSR.