基于Gabor变换与自组织稀疏RAM的N-tuple神经网络的人脸识别方法

本文提出了一种采用首先对人脸图像进行Gabor变换，然后由自组织稀疏RAM的N-tuple神经网络进行训练识别的方法，通过大量实验证明，该方法在较少训练样本下条件下，能够取得较高的识别率。     

镜像图与粗细层次结合的稀疏人脸识别方法研究

人脸在实际环境中,伴随着各种不可预知的情况,会呈现出复杂多变的特性.为了提高人脸识别率及更好的显示人脸特征,本文提出一种镜像图与粗细层次结合的稀疏识别新方法.该方法首先利用人脸的镜面性生成新的人脸图像,将原来的人脸训练样本和新生成的镜像图样本结合起来,使用粗细层次结合的分类方法来进行识别.新方法一方面增加了训练样本的数目,克服由于光照和姿态等外部因素带来的影响,另一方面选取合适的训练样本,丢掉不合适样本对于人脸识别所造成的不利影响.实验结果表明,新方法在人脸识别率上有了明显的提高.     

基于低秩特征脸与协同表示的人脸识别算法

在人脸识别中,人脸图像往往受到表情、光照、遮挡、姿态变化的影响,对此本文提出一种基于低秩特征脸与协同表示的人脸识别算法。该算法先用低秩矩阵恢复算法分解出训练样本图像的误差图像,再分别对训练样本与误差图像提取特征构造特征字典,计算测试样本图像特征字典下的协同表示系数,最后通过重构误差进行分类。通过AR和ORL人脸库进行实验,结果表明,本文提出的人脸识别算法的识别率、识别速率得到有效提高。     

Single sample per person face recognition with KPCANet and a weighted voting scheme

Most current methods of facial recognition rely on the condition of having multiple samples per person available for feature extraction. In practical applications, however, only one sample may be available for each person to train a model with. As a result, many of the traditional methods fall short, leaving the challenge of facial recognition greater than ever. To deal with this challenge, this study addresses a face recognition algorithm based on a kernel principal component analysis network (KPCANet) and then proposes a weighted voting method. First, the aligned face image is partitioned into several non-overlapping patches to form the training set. Next, a KPCANet is used to obtain filters and feature banks. Finally, the identification of the unlabeled probe occurs through the application of the weighted voting method. Based on several widely used face datasets, the results of the experiments demonstrate the superiority of the proposed method.     

融合原始样本和虚拟样本的人脸识别算法

由于有限的存储容量和捕获图片的时间,实际的人脸识别系统往往只能获得少量的训练样本,但是,在小训练样本情况下大多数人脸识别算法都会遇到困难.因此,为了提高人脸识别的分类正确率,提出了一种融合原始样本和虚拟样本的人脸识别方法.该方法先利用人脸的对称性来构造虚拟训练样本;然后,利用协同表示方法分别对原始训练样本和虚拟训练样本进行分析,并且分别得到每一类训练样本的重建误差;最后,将原始训练样本和虚拟训练样本的同一类重建误差进行加权融合并得到最终的分类结果.大量的实验结果比较分析表明,该方法可以获得更好的识别效果.     

基于块双向Fisher线性判别分析人脸识别

为解决二维Fisher线性判别(2DFLD)分析需要较多系数用以表示图像的特征阵、只考虑了图像的列间相关性从而忽略行间相关性以及作为全局特征提取方法可能会失去一些重要的局部特征等问题,提出一种基于块双向二维Fisher线性判别分析(B2DFLD)算法。首先利用块图像获取保持重要局部信息;然后基于行列双向投影,获取提取特征信息;最后计算特征阵的Frobenius距离,并进行分类。在ORL、YALE与FERET人脸数据库上进行了实验,并同传统的8种人脸识别方法比较。实验结果表明,在确定图像块大小、改变训练样本数以及特征维数的前提下,本文方法的最好识别率都高于93.08,平均误识率高于0.15,明显优于其他方法,表明本文方法对有光照、表情以及遮挡的人脸图像识别具有较高的鲁棒性。     

基于HOG低秩恢复与协同表征的人脸识别方法

在获取到的人脸图像不完备以及人脸图像在有遮挡、光照、表情的变化或受到噪声污染时,识别率就会变得十分低,针对这一问题,本文提出了一种基于HOG低秩恢复与协同表征的人脸识别算法HLRR_CRC.首先采用低秩恢复算法得到训练样本和测试样本的干净人脸图像,然后对测试样本中干净的人脸图像和训练样本中干净的人脸图像分别进行HOG特征提取,得到HOG特征向量,以此特征向量为基础,得到测试样本特征矢量的协同表示,最后,通过规则化残差进行分类.在ORL、Extended Yale B和AR数据库上进行测试,实验结果表明,本文算法对光照、噪声较鲁棒,相比于当前的人脸识别算法,本文算法在恶劣光照和噪声下的识别率平均提高29.6％.     

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。     

Facial Recognition Using Multisensor Images Based on Localized Kernel Eigen Spaces

A feature selection technique along with an information fusion procedure for improving the recognition accuracy of a visual and thermal image-based facial recognition system is presented in this paper. A novel modular kernel eigenspaces approach is developed and implemented on the phase congruency feature maps extracted from the visual and thermal images individually. Smaller sub-regions from a predefined neighborhood within the phase congruency images of the training samples are merged to obtain a large set of features. These features are then projected into higher dimensional spaces using kernel methods. The proposed localized nonlinear feature selection procedure helps to overcome the bottlenecks of illumination variations, partial occlusions, expression variations and variations due to temperature changes that affect the visual and thermal face recognition techniques. AR and Equinox databases are used for experimentation and evaluation of the proposed technique. The proposed feature selection procedure has greatly improved the recognition accuracy for both the visual and thermal images when compared to conventional techniques. Also, a decision level fusion methodology is presented which along with the feature selection procedure has outperformed various other face recognition techniques in terms of recognition accuracy.      

混合样本协同表示算法的人脸识别研究

在人脸识别中,人脸图像受到表情、光照、遮挡、姿态变化、特别是训练样本数量的影响,而现实中经常只获得少量的训练样本,由于原始样本生成虚拟样本可以增加训练样本的数量,分析提出原始样本与轴对称样本融合的协同表示算法。首先生成镜像样本与轴对称样本,再在协同表示分类器下分类,最后加权值融合,分析不同权值下的人脸识别率。实验结果显示原始样本、镜像样本与轴对称样本融合能提高识别率,而原始样本与轴对称样本融合的识别率更加优越,较原始样本,识别率提高2%~9%,比原始样本与镜像样本融合高1%~5%。结果表明本文提出方法能有效提高人脸识别率。     

Face recognition using position-dictionaries and region covariance feature

In this paper, a new sparsity formulation called position-dictionary based sparse representation is developed for frontal face recognition. Different from the sparse representation based classification (SRC) method and the Gabor-feature based SRC (GSRC) method which both employ a global dictionary to decompose image patches, the proposed method constructs a position-dictionary for each location using training patches in the corresponding location since they resemble each other and are more likely to favor the same atoms. Sparse coefficients of each position-patch can be obtained by solving an \(l_{1}\) -norm minimization problem. For each face image, sparse coefficients of position-patches are pooled to construct a discriminative upper level feature to represent face image. PCA is used to perform dimension reduction. Each testing sample is represented as a sparse linear combination of all training samples, and recognition is accomplished by evaluating which class of training samples leads to the minimum reconstruction error. We compared the proposed method with SRC and GSRC method on three benchmark face databases. Experimental results show that the proposed method achieves higher recognition rates and is robust to a certain degree of occlusions.     

采用新型纹理特征的2DLDA人脸识别算法

针对现有基于纹理特征的人脸识别算法中纹理特征维数偏大且对噪声较敏感等不足,提出了用于描述人脸图像大尺度局部特征的中心四点二元模式（Center Quad Binary Pattern, C-QBP）和用于描述图像小尺度局部特征的简化四点二元模式（Simplified Quad Binary Pattern, S-QBP）两种互补的新型纹理特征。在此基础上,实现基于新型纹理特征的2DLDA人脸识别算法。首先对人脸图像进行多级分割,再对所产生的图像块提取C-QBP和S-QBP纹理特征,构建纹理特征矩阵。最后,采用2DLDA子空间学习算法实现基于新型纹理特征的人脸识别。实验结果表明,本文所提出的人脸识别算法的识别率明显高于其他基于纹理特征和子空间学习的人脸识别算法。当每一类训练样本数统一设置为5,特征维数为48×4时,在ORL人脸库上,本文所提出的人脸识别算法的识别率达98.68%;在YALE人脸库上,特征维数为48×36时,识别率达99.42%;在FERET人脸库上,特征维数为48×26时,识别率为91.73%。      

改进投影梯度非负矩阵分解的单训练样本特征提取研究

人脸识别是当前人工智能和模式识别的研究热点。非负矩阵分解(NMF)能够反映样本的局部的内在的联系,可用于单样本特征提取,但时间复杂度较高。投影梯度(Projected Gradient,PG)优化方法大幅降低了NMF约束优化迭代问题的时间复杂度,但是单训练样本存在对本类信息量描述不足的缺点。为此,该文提出了一种基于改进的投影梯度非负矩阵分解 (Improved Projected Gradient Non-negative Matrix Factorization,IPGNMF) 的单训练样本特征提取方法。在进行PGNMF算子之前,先将训练样本作Gabor分解,分解后的Gabor子图像在各个方向上可以更加丰富的描述样本特征,最后将各个Gabor子图像的PGNMF特征进行融合,作为最终的识别特征。在对人脸库ORL,YEL与FERET的识别实验中,与经典的特征提取方法比较,证明了可以有效地解决单训练样本人脸识别的问题。     

Textural feature based face recognition for single training images

A novel face recognition algorithm using single training face image is proposed. The algorithm is based on textural features extracted using the 2D log Gabor wavelet. These features are encoded into a binary pattern to form a face template which is used for matching. Experimental results show that on the colour FERET database the accuracy of the proposed algorithm is higher than the local feature analysis (LFA) and correlation filter (CF) based face recognition algorithms even when the number of training images is reduced to one. In comparison with recent single training image based face recognition algorithms, the proposed 2D log Gabor wavelet based algorithm shows an improvement of more than 3% in accuracy.     

基于2DDPCA人脸识别算法

主成分分析法(PCA)是人脸识别传统方法之一,是模式识别中一种普遍的线性组合算法.传统PCA算法因光照等外界因素和计算量较大等问题导致识别率较低.为了抑制这些缺点,主要研究基于PCA人脸识别算法改进的二维主成分分析法(2DPCA)和在2DPCA算法的基础上进行第二次特征提取的2DDPCA算法,并对PCA,2DPCA,2DDPCA这3种人脸识别算法在ORL和Yale人脸数据库上进行实验.实验主要从两方面进行分析,特征向量的维数、训练样本数与识别率的关系以及3种方法分别在数据库的时间对比.实验结果表明,提出的2DDPCA算法在不明显降低识别率的基础上,能有效提高识别速率,重建性能好.     

角度空间三元组损失微调的人脸识别

针对角度Softmax损失强约束存在的问题,提出一种用角度空间三元组损失对角度Softmax损失预训练模型进行微调的算法。算法首先对原来的卷积神经网络结构进行改进,将1×1卷积核与池化层加在不同残差块间,以进行选择更有效的特征。然后用角度空间下的三元组损失对预训练模型进行微调,以降低困难样本的强约束条件。最后在测试时,分别提取原始人脸图像特征和水平翻转的人脸图像特征,对两个特征相加作为最终的人脸特征表达,以丰富人脸特征信息,提高识别率。实验结果表明,在LFW和YTF人脸数据集分别取得了99.25%和94.52%的识别率,在大规模人脸身份识别中,本文提出的方法在仅用单模型和比较小的训练集就能有效地提高人脸识别率。     

通用学习框架结合2DPCA的鲁棒人脸识别

针对现有的人脸识别算法由于光照、表情、姿态、伪装等变化而严重影响识别性能的问题,提出了一种基于通用学习框架结合2DPCA的鲁棒人脸识别算法。首先借助于额外的通用训练样本集进行样本的叠加以增加训练样本的数量;然后利用经典的2DPCA算法进行特征提取;最后,利用最近邻分类器对人脸进行分类并完成最终的人脸识别。在基准人脸数据库ORL、FERET及鲁棒人脸数据库AR、扩展YaleB上的实验验证了该算法的有效性及鲁棒性,实验结果表明,相比其他几种人脸识别算法,提出的算法不仅提高了人脸识别率,而且大大地减少了识别所用时间,有望应用于实时鲁棒人脸自动识别系统中。     

Kernel Discriminant Embedding in face recognition

In this paper, we present a novel and effective feature extraction technique for face recognition. The proposed technique incorporates a kernel trick with Graph Embedding and the Fisher’s criterion which we call it as Kernel Discriminant Embedding (KDE). The proposed technique projects the original face samples onto a low dimensional subspace such that the within-class face samples are minimized and the between-class face samples are maximized based on Fisher’s criterion. The implementation of kernel trick and Graph Embedding criterion on the proposed technique reveals the underlying structure of data. Our experimental results on face recognition using ORL, FRGC and FERET databases validate the effectiveness of KDE for face feature extraction.     

小样本条件下基于全局和局部特征融合的人脸识别

针对线性判别分析的小样本空间问题,提出了一种基于类向量的融合全局和局部特征的人脸识别算法.首先,提取人脸的全局特征;然后将人脸分割成6个关键部分,并用一种新的基于Gabor小波的方法提取特征;其次,将全局和局部特征融合,得出样本的特征向量;再次,得出每类样本的类向量并据此得出一种新的投影准则;最后,将类向量和试验样本分别进行投影,根据其欧氏距离的大小得出试验人脸的最终类.试验表明本文算法不仅能有效解决小样本空间问题,而且计算速度快,识别率高,应用前景良好.     

Deep low-rank feature learning and encoding for cross-age face recognition

Cross-age face recognition (CAFR) is a challenging task, due to significant intra-personal variations. Furthermore, the training and testing data may contain random noise components. To address these issues, this paper proposes a deep low-rank feature learning and encoding method. Firstly, our method employs manifold learning in the low-rank optimization, which preserves the global and local structure of the data samples, while learning the clean low-rank features. Secondly, we encode the low-rank features using our locality-constrained feature encoding method, which learns an age-insensitive codebook from training data, and enables the intra-class samples to share the same local bases in a codebook. In the testing stage, the gallery and probe features are encoded by the learned codebook, which represents the images of the same identity by similar codewords for recognition. Furthermore, the periocular region of human faces is investigated for CAFR. Extensive experiments on five datasets demonstrate the effectiveness of our method.