通信辐射源的潜在细微特征提取方法

为了充分挖掘高维特征空间中辐射源的细微特征, 提出一种基于全局潜在低秩表示(Global Latent Low Rank Representation, GLat-LRR)的通信辐射源潜在细微特征提取方法.首先, 提取通信辐射源信号的瞬时频率, 通过傅里叶变换将信号投影到高维特征空间; 挖掘特征样本之间全局的低秩结构和维度之间全局的潜在低秩关系, 将特征样本集作为整体应用到潜在低秩表示模型中, 利用维度之间低秩关系得到特征样本集的潜在部分矩阵, 每个列向量即为每个通信辐射源信号的潜在细微特征向量.在实际采集的同厂家同型号FM电台数据集上, 该方法提取的潜在细微特征能够显著提高通信辐射源个体识别的性能.     

Sparse representation for face recognition by discriminative low-rank matrix recovery

This paper proposes a discriminative low-rank representation (DLRR) method for face recognition in which both the training and test samples are corrupted owing to variations in occlusion and disguise. The proposed method extends the sparse representation-based classification algorithm by incorporating the low-rank structure of data representation. The DLRR algorithm recovers a clean dictionary with enhanced discrimination ability from the corrupted training samples for sparse representation. Simultaneously, it learns a low-rank projection matrix to correct corrupted test samples by projecting them onto their corresponding underlying subspaces. The dictionary elements from different classes are encouraged to be as independent as possible by regularizing the structural incoherence of the original training samples. This leads to a compact representation of a corrected test sample by a linear combination of more dictionary elements from the corrected class. The experimental results on benchmark databases show the effectiveness and robustness of our face recognition technique.     

Action recognition via structured codebook construction

Bag-of-words models have been widely used to obtain the global representation for action recognition. However, these models ignored the structure information, such as the spatial and temporal contextual information for action representation. In this paper, we propose a novel structured codebook construction method to encode spatial and temporal contextual information among local features for video representation. Given a set of training videos, our method first extracts local motion and appearance features. Next, we encode the spatial and temporal contextual information among local features by constructing correlation matrices for local spatio-temporal features. Then, we discover the common patterns of movements to construct the structured codebook. After that, actions can be represented by a set of sparse coefficients with respect to the structured codebook. Finally, a simple linear SVM classifier is applied to predict the action class based on the action representation. Our method has two main advantages compared to traditional methods. First, our method automatically discovers the mid-level common patterns of movements that capture rich spatial and temporal contextual information. Second, our method is robust to unwanted background local features mainly because most unwanted background local features cannot be sparsely represented by the common patterns and they are treated as residual errors that are not encoded into the action representation. We evaluate the proposed method on two popular benchmarks: KTH action dataset and UCF sports dataset. Experimental results demonstrate the advantages of our structured codebook construction.     

基于深度分层特征表示的行人识别方法

该文针对行人识别中的特征表示问题,提出一种混合结构的分层特征表示方法,这种混合结构结合了具有表示能力的词袋结构和学习适应性的深度分层结构。首先利用基于梯度的HOG局部描述符提取局部特征,再通过一个由空间聚集受限玻尔兹曼机组成的深度分层编码方法进行编码。对于每个编码层,利用稀疏性和选择性正则化进行无监督受限玻尔兹曼机学习,再应用监督微调来增强分类任务中视觉特征表示,采用最大池化和空间金字塔方法得到高层图像特征表示。最后采用线性支持向量机进行行人识别,提取深度分层特征遮挡等与目标无关部分自然分离,有效提高了后续识别的准确性。实验结果证明了所提出方法具有较高的识别率。     

基于统计学习优化SIFT的面部遮挡人脸识别

针对传统的人脸识别算法受面部遮挡的影响导致很难兼顾鲁棒性和保持原始图像核心信息的问题,本文提出了一种基于统计学习优化尺度不变特征变换的面部遮挡人脸识别算法。首先,利用SIFT将所有给定训练图像用一组局部特征描述符表示出来;然后,通过执行统计学习获得正常脸部图像SIFT特征的概率分布函数,利用获得的概率分布函数在新观察到的测试图像中检测异常SIFT特征;最后,计算测试图像与训练图像之间的相似度,并利用K近邻分类器完成人脸识别。在AR人脸数据库上的实验验证了本文算法的有效性及可靠性,实验结果表明,相比其它几种较为先进的人脸识别算法,本文算法取得了更强的识别鲁棒性。     

Discriminative low-rank embedding with manifold constraint for image feature extraction and classification

The robustness against noise, outliers, and corruption is a crucial issue in image feature extraction. To address this concern, this paper proposes a discriminative low-rank embedding image feature extraction algorithm. Firstly, to enhance the discriminative power of the extracted features, a discriminative term is introduced using label information, obtaining global discriminative information and learning an optimal projection matrix for data dimensionality reduction. Secondly, manifold constraints are incorporated, unifying low-rank embedding and manifold constraints into a single framework to capture the geometric structure of local manifolds while considering both local and global information. Finally, test samples are projected into a lower-dimensional space for classification. Experimental results demonstrate that the proposed method achieves classification accuracies of 95.62%, 95.22%, 86.38%, and 86.54% on the ORL, CMUPIE, AR, and COIL20 datasets, respectively, outperforming dimensionality reduction-based image feature extraction algorithms.     

基于判别低秩矩阵恢复和稀疏表示的车标识别

针对现有的车标识别方法无法较好地处理阴影、遮挡、污损等情况下识别率低的问题,提出了基于判别低秩矩阵恢复和稀疏表示的车标识别方法。文中采用判别低秩矩阵恢复来纠正效果较差的训练样本,并通过学习一个低秩投影矩阵,将待测样本特征矩阵投影到相应低秩子空间来恢复干净的测试样本。并采用稀疏表示方式进行分类识别。同时,在Medialab LPR Database数据集上进行了对比实验,实验结果表明,该识别方法的性能要优于当前其他识别方法     

Quality assessment of screen content images based on multi-stage dictionary learning

In this paper, we propose an effective method for quality assessment of screen content images (SCIs) based on multi-stage dictionary learning. To simulate the brain’s layered processing of signals, we proposed a hierarchical feature extraction strategy, which is called multi-stage dictionary learning, to simulate the hierarchical information processing of brain. First, the standard deviation of normalized map obtained from training image is used to select the training data in a certain proportion, which can ensure the learning efficiency and reduce the training burden. Next, the reconstructed map is weighted as the input of the next-stage dictionary learning. Then using the trained dictionary, the sparse representation is applied to extract features. Meanwhile, considering that some important features may be ignored in the process of multi-stage dictionary learning, we use Log Gabor filter to extract feature maps, and then calculate the correlation between feature maps as another kind of compensation features. Final, for the two feature sets, we choose SVR and feature codebook to learn two objective scores, and then use the adaptive weighting strategy to get the final objective quality score. Experimental results show that the proposed method is superior to several mainstream SCIs metrics on two publicly available databases.     

A novel recurrent hybrid network for feature fusion in action recognition

Action recognition in video is one of the most important and challenging tasks in computer vision. How to efficiently combine the spatial-temporal information to represent video plays a crucial role for action recognition. In this paper, a recurrent hybrid network architecture is designed for action recognition by fusing multi-source features: a two-stream CNNs for learning semantic features, a two-stream single-layer LSTM for learning long-term temporal feature, and an Improved Dense Trajectories (IDT) stream for learning short-term temporal motion feature. In order to mitigate the overfitting issue on small-scale dataset, a video data augmentation method is used to increase the amount of training data, as well as a two-step training strategy is adopted to train our recurrent hybrid network. Experiment results on two challenging datasets UCF-101 and HMDB-51 demonstrate that the proposed method can reach the state-of-the-art performance.     

改进非负矩阵分解的神经网络人脸识别

为了提高人脸识别正确率,提出基于改进非负矩阵分解的神经网络人脸识别算法。首先利用改进的非负矩阵分解对人脸图像进行特征提取,提高非负矩阵分解速度。接着将提取出的特征信息作为神经网络学习入口进行特征训练,由于神经网络在学习过程中,容易出现局部最小值且收敛速度慢等问题,为此采用改进的遗传算法对神经网络进行优化处理,获得最终的人脸识别结果。实验结果表明:利用改进的非负矩阵分解方法能够降低神经网络的分类训练负荷量和运算量,提高人脸识别识别率。通过和各种方法比较可知,本方法的人脸识别率都较高。本方法人脸特征分解速度快,提高了神经网络训练前期精度和收敛速度,使得人脸识别正确率高。当特征向量个数达到40以上时,人脸识别正确率保持95%以上。     

一种具有隐蔽色特征物体的图像分类方法研究

针对图像中某几类物体具有相似颜色特征而导致的分类困难问题,本文提出了一种具有隐蔽色特征物体的图像分类方法.该方法针对可见光图像中具有颜色隐蔽性物体而难以区分的问题,通过将二维图像的邻域像素空间特征与高光谱图像的谱段特征相结合并使用改进的局部线性嵌入降维算法实现了空谱联合的特征降维,最终利用主动学习胶囊网络训练高光谱数据...     

应用神经网络的图像分类矢量量化编码

矢量量化作为一种有效的图像数据压缩技术，越来越受到人们的重视。设计矢量量化器的经典算法ＬＢＧ算法，由于运算复杂，从而限制了矢量量化的实用性。本文讨论了应用神经网络实现的基于边缘特征分类的矢量量化技术。它是根据人的视觉系统对图象的边缘的敏感性，应用模式识别技术，在对图像编码前，以边缘为特征对图像内容分类，然后再对每类进行矢量量化。除特征提取是采用离散余弦变换外，图像的分类和矢量量化都是由神经网络完成     

Extended linear regression for undersampled face recognition

Linear Regression Classification (LRC) is a newly-appeared pattern recognition method, which formulates the recognition problem in terms of class-specific linear regression with sufficient training samples per class. In this paper, we extend LRC via intraclass variant dictionary and SVD to undersampled face recognition where there are very few, or even only one, training sample per class. Intraclass variant dictionary is adopted in undersampled situation to represent the possible variation between the training and testing samples. Three types of methods, quasi-inverse, ridge regularization and Singular Value Decomposition (SVD), are designed to solve low-rank problem of data matrix. Then the whole algorithm, named Extended LRC (ELRC), is presented for face recognition via intraclass variant dictionary and SVD. The experimental results on three well-known face databases show that the proposed ELRC has better generalization ability and is more robust to classification than many state-of-the-art methods in undersampled situation.     

Learned local Gabor patterns for face representation and recognition

In this paper, we propose Learned Local Gabor Patterns (LLGP) for face representation and recognition. The proposed method is based on Gabor feature and the concept of texton, and defines the feature cliques which appear frequently in Gabor features as the basic patterns. Different from Local Binary Patterns (LBP) whose patterns are predefined, the local patterns in our approach are learned from the patch set, which is constructed by sampling patches from Gabor filtered face images. Thus, the patterns in our approach are face-specific and desirable for face perception tasks. Based on these learned patterns, each facial image is converted into multiple pattern maps and the block-based histograms of these patterns are concatenated together to form the representation of the face image. In addition, we propose an effective weighting strategy to enhance the performances, which makes use of the discriminative powers of different facial parts as well as different patterns. The proposed approach is evaluated on two face databases: FERET and CAS-PEAL-R1. Extensive experimental results and comparisons with existing methods show the effectiveness of the LLGP representation method and the weighting strategy. Especially, heterogeneous testing results show that the LLGP codebook has very impressive generalizability for unseen data.     

基于双流特征融合的FMCW雷达人体连续动作识别

本文提出了一种基于双流特征融合的FMCW雷达人体连续动作识别方法。首先对人体动作雷达回波信号进行预处理得到距离时间域图与微多普勒时频谱图,之后分别对两个不同维度的图像进行主成分分析提取对应特征并选取相同时间段的主成分分析结果进行融合得到双流融合特征,最后将双流融合特征输入到Bi-LSTM网络中训练与测试,网络对每个时间段的输入特征产生与之对应的动作类别输出从而实现连续人体动作识别。实验结果表明,当采用双流融合特征作为Bi-LSTM网络的输入时平均识别准确率要高于只采用距离时间特征或微多普勒特征作为网络输入时的平均识别准确率。     

基于深度信念网络的事件识别

事件识别是信息抽取的重要基础.为了克服现有事件识别方法的缺陷,本文提出一种基于深度学习的事件识别模型.首先,我们通过分词系统获得候选词并将它们分为五种类型.然后选择六种识别特征并制定相应的特征表示规则用来将词转化为向量样例.最后我们通过深度信念网络抽取词的深层语义信息,并由Back-Propagation(BP)神经网络识别事件.实验显示模型最高F值达85.17%.同时,本文还提出了一种融合无监督和有监督两种学习方式的混合监督深度信念网络,该网络能够提高识别效果(F值达89.2%)并控制训练时间(增加27.50%).     

一种基于视觉词袋模型的人脸识别方法

针对人脸图像因受表情、光照、角度等因素影响,导致人脸识别率较低的状况,提出了一种基于视觉词袋模型的人脸识别方法。该方法首先对图像进行分块并提取局部特征,其次利用训练样本的所有局部特征训练全局的混合高斯模型,然后以此为初始化训练单张图像的混合高斯模型,生成该图像全局特征向量,最后用PLDA进行人脸识别。通过在LFW数据库上进行实验,结果显示本方法的识别率高于传统的特征提取方法,证明了本方法具有更强的识别性能。     

Automatic image orientation detection

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a learning vector quantizer (LVQ) can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show how principal component analysis (PCA) and linear discriminant analysis (LDA) can be used as a feature extraction mechanism to remove redundancies in the high-dimensional feature vectors used for classification. The proposed method is compared with four different commonly used classifiers, namely k-nearest neighbor, support vector machine (SVM), a mixture of Gaussians, and hierarchical discriminating regression (HDR) tree. Experiments on a database of 16 344 images have shown that our proposed algorithm achieves an accuracy of approximately 98% on the training set and over 97% on an independent test set. A slight improvement in classification accuracy is achieved by employing classifier combination techniques.     

Sequential image deep learning-based Wi-Fi human activity recognition method

For the problems existing in most of the researches,such as weak anti-noise ability,incompatible signal size and insufficient feature extraction of deep-learning-based Wi-Fi human activity recognition,a kind of sequential image deep learning-based recognition method was proposed.Based on the idea of sequential image deep learning,a series of image frames were reconstructed from time-varied Wi-Fi signal to ensure the consistency of input size.In addition,a low-rank decomposition method was innovatively designed to separate low-rank activity information merged in noises.Finally,a deep model combining temporal stream and spatial stream was proposed to automatically capture the spatiotemporal features from length-varied image sequences.The proposed method was extensively tested in WiAR dataset and self collected dataset.The experimental results show the proposed method could achieve the accuracy of 0.94 and 0.96,which indicate its high-accuracy performance and robustness in pervasive environments.