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.     

Improving representation-based classification for robust face recognition

The sparse representation classification (SRC) method proposed by Wright et al. is considered as the breakthrough of face recognition because of its good performance. Nevertheless it still cannot perfectly address the face recognition problem. The main reason for this is that variation of poses, facial expressions, and illuminations of the facial image can be rather severe and the number of available facial images are fewer than the dimensions of the facial image, so a certain linear combination of all the training samples is not able to fully represent the test sample. In this study, we proposed a novel framework to improve the representation-based classification (RBC). The framework first ran the sparse representation algorithm and determined the unavoidable deviation between the test sample and optimal linear combination of all the training samples in order to represent it. It then exploited the deviation and all the training samples to resolve the linear combination coefficients. Finally, the classification rule, the training samples, and the renewed linear combination coefficients were used to classify the test sample. Generally, the proposed framework can work for most RBC methods. From the viewpoint of regression analysis, the proposed framework has a solid theoretical soundness. Because it can, to an extent, identify the bias effect of the RBC method, it enables RBC to obtain more robust face recognition results. The experimental results on a variety of face databases demonstrated that the proposed framework can improve the collaborative representation classification, SRC, and improve the nearest neighbor classifier.     

Face recognition based on symmetrical virtual image and original training image

In face representation-based classification methods, we are able to obtain high recognition rate if a face has enough available training samples. However, in practical applications, we only have limited training samples to use. In order to obtain enough training samples, many methods simultaneously use the original training samples and corresponding virtual samples to strengthen the ability of representing the test sample. One is directly using the original training samples and corresponding mirror samples to recognize the test sample. However, when the test sample is nearly symmetrical while the original training samples are not, the integration of the original training and mirror samples might not well represent the test samples. To tackle the above-mentioned problem, in this paper, we propose a novel method to obtain a kind of virtual samples which are generated by averaging the original training samples and corresponding mirror samples. Then, the original training samples and the virtual samples are integrated to recognize the test sample. Experimental results on five face databases show that the proposed method is able to partly overcome the challenges of the various poses, facial expressions and illuminations of original face image.     

Determination of candidate subjects for better recognition of faces

In order to improve the accuracy of face recognition and to solve the problem of various poses, we present an improved collaborative representation classification (CRC) algorithm using original training samples and the corresponding mirror images. First, the mirror images are generated from the original training samples. Second, both original training samples and their mirror images are simultaneously used to represent the test sample via improved collaborative representation. Then, some classes which are “close” to the test sample are coarsely selected as candidate classes. At last, the candidate classes are used to represent the test sample again, and then the class most similar to the test sample can be determined finely. The experimental results show our proposed algorithm has more robustness than the original CRC algorithm and can effectively improve the accuracy of face recognition.     

Sample partition and grouped sparse representation

Recently, conventional representation-based classification (RBC) methods demonstrate promising performance in image recognition. However, conventional RBCs only use a kind of deviations between the test sample and the linear combination of training samples of each class to perform classification. In many cases, a single kind of deviations corresponding to each class cannot effectively reflect the difference between the test sample and reconstructed sample of each class. Moreover, in practical applications, limited training samples are not able to reflect the possible changes of the image sufficiently. In this paper, we propose a novel scheme to tackle the above-mentioned problems. Specifically, we first use the original training samples to generate corresponding mirror samples. Thus, the original sample set and its mirror counterpart are treated as two separate training groups. Secondly, we perform collaborative representation classification on these two groups from which each class leads to two kinds of deviations, respectively. Finally, we fuse two kinds of deviations of each class and their correlation coefficient to classify the test sample. The correlation coefficient is defined for two kinds of deviations of each class. Experimental results on four databases show the proposed scheme can improve the recognition rate in image-based recognition.     

共享空间基-逐类剩余空间基混合稀疏表示人脸识别算法

针对传统训练样本字典学习未利用类共有信息的不足,引入共享空间和与类别相关的剩余空间,提出了共享空间基-逐类剩余空间基混合稀疏表示人脸识别的算法。该算法首先提取训练样本主成分分析(PCA)特征,获取无标记的共享空间基及其重构样本得到类共有信息;然后结合原始样本得到差分训练集合,并引入类间差异信息构建逐类特异性剩余空间基;最后融合共享空间基和剩余空间基,利用残差判别函数完成模式分类。该方法不仅利用混合空间的正交特性,而且发挥剩余空间的鉴别能力和共享信息稀疏逼近的作用,使结构性字典和模式分类紧密结合。该方法的有效性,分别通过用AR、CMU PIE、Extended Yale B人脸数据库进行的实验得到验证。     

融合2D-PCA及稀疏表示的掌纹识别方法

提出一种基于稀疏表示的掌纹识别方法,该方法借鉴二维主成分分析(PCA)良好的数据压缩属性和较快的特征提取速度,生成掌纹特征图像.二维PCA不仅克服了一维PCA数据维数过大不易计算的缺点,而且保留了原始图像的数据结构,提取的特征能更好的代表原始图像.为了便于稀疏表达,对提取的掌纹特征图像利用一维主成分分析进行二次特征提取,得到训练样本.虽然此处使用了一维PCA,但是由于这是二次特征提取,提取的特征还是保留了原始图像的数据结构,相比单纯的一维PCA,提高了识别率.利用训练样本构造出冗余字典,并采用稀疏表示理论将测试样本表示为字典原子的线性组合,然后根据表示系数的稀疏性与稀疏集中度实现分类识别.由于该方法利用了表达系数的稀疏性,因此减小了算法的时间和空间复杂度.实验表明,针对香港理工大学的MSpalmprints Database,本文方法的识别率较传统方法有明显提高.     

基于改进判别字典学习的故障诊断方法

近年来,基于稀疏表示的分类技术在模式识别中取得一定的成功。该框架中,字典的学习和分类器的训练通常是两个独立的模块,降低了方法的识别精度。针对以上问题,提出了一种特征提取和模式识别相融合的改进判别字典学习模型,将重构误差项、稀疏编码判别项及分类误差项进行了整合,并用K奇异值分解算法对目标函数进行优化,实现了字典和分类器的同步学习。该方法先对原始信号进行经验模态分解,并从分解的本征模态函数中提取时、频特征,形成故障样本;然后将训练样本输入改进模型用K奇异值分解优化;最后用习得字典及分类器权重对测试样本进行识别。实验结果表明：该算法不但适用于小样本故障问题,而且鲁棒性和分类性能都明显高于其它算法。         

A supervised dimensionality reduction method-based sparse representation for face recognition

The sparse representation-based classification (SRC) method is a powerful tool to present high-dimensionality data and its superiority in many fields, especially in face recognition application has been proved. With sparsity appropriately harnessed, the SRC can solve face classification problems caused by varying expression, illumination as well as occlusion and disguise. However, face images as high-dimensionality data are usually noisy and the dimensionality is always larger than the number of training sample in real-world applications, which bring a disadvantage for the performance of SRC. Therefore, it is beneficial to perform dimensionality reduction (DR) before utilizing the SRC method. But most prevalent DR methods have no direct connection to SRC. In this paper, we proposed a supervised DR algorithm which suits SRC well and improves the discriminating ability in the low-dimensionality space. The proposed method utilizes the fisher discriminant criterion and low-dimensionality reconstructive restriction to extract the discriminating structure of data. The extensive experiments on public face databases verified the effectiveness of the supervised DR with the model of sparse representation.     

Biomedical Event Extraction Using a New Error Detection Learning Approach Based on Neural Network

Supervised machine learning approaches are effective in text mining, but their success relies heavily on manually annotated corpora. However, there are limited numbers of annotated biomedical event corpora, and the available datasets contain insufficient examples for training classifiers; the common cure is to seek large amounts of training samples from unlabeled data, but such data sets often contain many mislabeled samples, which will degrade the performance of classifiers. Therefore, this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data. First, we construct the mislabeled dataset through error data analysis with the development dataset. The sample pairs’ vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network. Following this, the sample identification strategy is proposed, using error detection based on pair representation for unlabeled data. With the latter, the selected samples are added to enrich the training dataset and improve the classification performance. In the BioNLP Shared Task GENIA, the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature. Our approach can effectively filter some noisy examples and build a satisfactory prediction model.     

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.     

增强联系鉴别分析及在人脸识别中的应用

针对人脸识别中的小样本问题,本文提出了一种名为增强联系鉴别分析的方法并应用人脸识别中.该方法利用将人脸局部流形的结构信息和样本的类别信息进行有效地结合进行维数约简,首先构建人脸数据的近邻图与类别联系图,然后通过解决在一定约束条件下的优化问题来获取低维鉴别流形特征,实现在低维空间中同一类人脸数据聚集,不同类别间的人脸数据间尽可能发散,从而可以更好的应用于分类.在AT&T和Yale人脸图像数据库上的实验结果表明该方法能有效的提高人脸识别的性能.     

一种快速的基于稀疏表示的人脸识别算法

基于稀疏表示的人脸识别算法（SRC）识别率相当高,但是当使用l1范数求最优的稀疏表示时,大大增加了算法的计算复杂度,矩阵随着维度的增加,计算时间呈几何级别上升,该文提出利用拉格朗日算法求解矩阵的逆的推导思路,用一种简化的伪逆求解方法来代替l1范数的计算,可将运算量较高的矩阵求逆运算转变为轻量级向量矩阵运算,基于AR人脸库的实验证明,维度高的时候识别率高达97%,同时,计算复杂度和开销比SRC算法大幅度降低95%。     

基于广义形态分量分析的降噪技术研究

针对强噪声环境中有用信号提取的难题,提出了基于广义形态分量分析的降噪方法。通过引入虚拟观测信号,将一维观测信号扩展为多维虚拟观测信号,再通过广义形态分量分析,实现观测信号的盲源分离,从而达到降噪的目的。通过仿真信号和齿轮磨损故障振动实验信号的研究结果表明：广义形态分量分析技术能有效分离强背景噪声中的微弱信号,有效提取故障特征,其降噪性能优于传统的独立分量分析。     

The attribute-trend-similarity method to improve learning performance for small datasets

Small data-set learning problems are attracting more attention because of the short product lifecycles caused by the increasing pressure of global competition. Although statistical approaches and machine learning algorithms are widely applied to extract information from such data, these are basically developed on the assumption that training samples can represent the properties of the whole population. However, as the properties that the training samples contain are limited, the knowledge that the learning algorithms extract may also be deficient. Virtual sample generation approaches, used as a kind of data pretreatment, have proved their effectiveness when handling small data-set problems. By considering the relationships among attributes in the value generation procedure, this research proposes a non-parametric process to learn the trend similarities among attributes, and then uses these to estimate the corresponding ranges that attribute values may be located in when other attribute values are given. The ranges of the attribute values of the virtual samples are then stepwise estimated using the triangular membership functions (MFs) built to represent the attribute sample distributions. In the experiment, two real cases are examined with four modelling tools, including the M5′ model tree (M5′), multiple linear regression, support vector regression and back-propagation neural network. The results show that the forecasting accuracies of the four modelling tools are improved when training sets contain virtual samples. In addition, the outcomes of the proposed procedure show significantly smaller predictive errors than those of other approaches.     

Human Action Recognition Based on Supervised Class-Specific Dictionary Learning with Deep Convolutional Neural Network Features

Human action recognition under complex environment is a challenging work. Recently, sparse representation has achieved excellent results of dealing with human action recognition problem under different conditions. The main idea of sparse representation classification is to construct a general classification scheme where the training samples of each class can be considered as the dictionary to express the query class, and the minimal reconstruction error indicates its corresponding class. However, how to learn a discriminative dictionary is still a difficult work. In this work, we make two contributions. First, we build a new and robust human action recognition framework by combining one modified sparse classification model and deep convolutional neural network (CNN) features. Secondly, we construct a novel classification model which consists of the representation-constrained term and the coefficients incoherence term. Experimental results on benchmark datasets show that our modified model can obtain competitive results in comparison to other state-of-the-art models.     

改进DCL的花卉子类细粒度分类算法

针对现有的单一细粒度识别模型不能识别无训练样本花卉子类这一实际情况,结合DCL与KNN提出了一种将细粒度特征映射到高维空间自动分类的方法,实现无训练样本的子类分类。同时针对同一花卉子类特征较为相似且可能存在类间样本不均衡问题,改进了DCL模型的损失函数(focal loss),通过对比损失(contrastive loss)加大子类的类间距,用focal loss平衡类别损失。最后在308类样本不均衡的牡丹花上进行实验。实验结果表明:改进算法后有训练样本的子类准确率为0.932,F1值为0.925,较原始DCL算法有了较大的提升,对未训练样本的子类准确率为0.903,F1值为0.888。     

Sound quality analysis of slide adjuster for automotive power seat using stepwise regression

This study has analyzed the effect of noise sources of power seat slide adjuster on sound quality and human sensitivity through statistical methods. First, sound quality analysis using sound quality metrics was performed to analyze objective data. Next, the subjective evaluation of sound quality was performed by a jury test. There were two types of sound sources used for the jury test; one was two original sounds measured in the operating test and the other one was eight virtual sound sources that were produced by amplifying a specific frequency of original sounds. It was designed to derive the causal relationship between each noise source and human sensitivity. Thirdly, we analyzed the correlation between the sound quality metrics and the sound pressure level of the noise source through the factor analysis. As a result, four independent variables were derived. Lastly, stepwise regression analysis was performed using four independent variables and the results of the jury test. The derived regression models had considerable explanatory power. From this, it was possible to understand the influence of the noise source of the seat slide adjuster on the sound quality and human sensitivity.     

用于水声目标识别的自适应遗传样本选择算法

针对训练样本集中含有噪声样本、冗余样本以及无关样本,导致分类系统分类性能下降、不稳定的水声目标识别问题,提出了一种新的自适应遗传样本选择算法(Adaptive Genetic Instance Selection Algorithm, AGISA)。算法先随机生成初始种群,接着利用设计的遗传算子(跨代选择、自适应交叉和简化最近邻变异)指导种群进化,每代中对分类贡献大且选择样本数目少的个体适应度值高。提取了实测3类水声目标的多域特征,进行样本选择和分类识别仿真实验,结果表明：AGISA可以选出有效样本子集,在样本维数下降约73%的情况下,支持向量机分类器的正确分类率能提高约2.5%;并且AGISA具有较好的收敛性、稳定性,所得优化样本子集具有较好泛化能力且能明显减少分类的时间。