Face Recognition Using Dense SIFT Feature Alignment

This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses,expressions and misalignments.We employ dense Scale-invariant feature transform (SIFT) feature matching as a generic transformation to roughly align training sampies;and then identify input facial images via an improved sparse representation model based on the aligned training samples.Compared with previous methods,the extensive experimental results demonstrate the effectiveness of our method for the task of face recognition on three benchmark datasets.     

图像集闭包建模的协同表示人脸识别算法

针对样本集距离分类算法忽略样本集内部变化的不足,利用图像多重描述提供的互补信息,提出图像集闭包建模的协同表示人脸识别算法。首先,扩展具有多重描述能力的图像集,图像的中等强度像素携带鉴别信息利用原始图像生成中等像素图像,镜像图像可增添图像细节信息利用原始图像产生镜像图像,将此两种源域图像与原始图像联合构成扩展的图像集。然后,以无参建模构建扩展的图像集为字典闭包,同类异源域的测试图像构成图像集且构建为测试闭包,借鉴协同表示思想利用字典学习迭代求解闭包系数。最后,采用残差判别函数进行模式分类。本文方法不仅构建具有多重描述能力的图像集,而且充分利用样本集内部关联性从而获得较好的分类结果。本文分别在ORL、GT（Georgia Tech Face Database）、CMU PIE人脸数据库上进行实验。      

一种基于稠密SIFT特征对齐的稀疏表达人脸识别算法

该文针对人脸图像受到非刚性变化的影响,如旋转、姿态以及表情变化等,提出一种基于稠密尺度不变特征转换(SIFT)特征对齐(Dense SIFT Feature Alignment, DSFA)的稀疏表达人脸识别算法。整个算法包含两个步骤：首先利用DSFA方法对齐训练和测试样本;然后设计一种改进的稀疏表达模型进行人脸识别。为加快DSFA步骤的执行速度,还设计了一种由粗到精的层次化对齐机制。实验结果表明：在ORL,AR和LFW 3个典型数据集上,该文方法都获得了最高的识别精度。该文方法比传统稀疏表达方法在识别精度上平均提高了4.3%,同时提高了大约6倍的识别效率。     

基于Fisher约束和字典对的图像分类

基于稀疏表示的分类方法由于其所具有的简单性和有效性获得了研究者的广泛关注,然而如何建立字典原子与类别信息间的联系仍然是一个重要的问题,与此同时大部分稀疏表示分类方法都需要求解受范数约束的优化问题,使得分类任务的计算较复杂。为解决上述问题,该文提出一种新的基于Fisher约束的字典对学习方法。新方法联合学习结构化综合字典和结构化解析字典,然后通过样本在解析字典上的映射直接求解稀疏系数矩阵;同时采用Fisher判别准则编码系数使系数具有一定的判别性。最后将新方法应用到图像分类中,实验结果表明新方法在提高分类准确率的同时还大大降低了计算复杂度,相较于现有方法具有更好的性能。     

Comparison of ICA approaches for facial expression recognition

Independent component analysis (ICA) and Gabor wavelets extract the most discriminating features for facial action unit classification by employing either a cosine similarity measure (CSM) classifier or support vector machines (SVMs). So far, only the ICA approach, which is based on the InfoMax principle, has been tested for facial expression recognition. In this paper, in addition to the InfoMax approach, another five ICA approaches extract features from two facial expression databases. In particular, the Extended InfoMax ICA, the undercomplete ICA, and the nonlinear kernel-ICA approaches are exploited for facial expression representation for the first time. When applied to images, ICA treats the images as being mixtures of independent sources and decomposes them into an independent basis and the corresponding mixture coefficients. Two architectures for representing the images can be employed yielding either independent and sparse basis images or independent and sparse distributions of image representation coefficients. After feature extraction, facial expression classification is performed with the help of either a CSM classifier or an SVM classifier. A detailed comparative study is made with respect to the accuracy offered by each classifier. The correlation between the accuracy and the mutual information of independent components or the kurtosis is evaluated. Statistically significant correlations between the aforementioned quantities are identified. Several issues are addressed in the paper: (i) whether features having super- and sub-Gaussian distribution facilitate facial expression classification; (ii) whether a nonlinear mixture of independent sources improves the classification accuracy; and (iii) whether an increased “amount” of sparseness yields more accurate facial expression recognition. In addition, performance enhancements by employing leave-one-set of expressions-out and subspace selection are studied. Statistically significant differences in accuracy between classifiers using several feature extraction methods are also indicated.     

Multi-pose 3D face recognition based on 2D sparse representation

The increasing availability of 3D facial data offers the potential to overcome the difficulties inherent with 2D face recognition, including the sensitivity to illumination conditions and head pose variations. In spite of their rapid development, many 3D face recognition algorithms in the literature still suffer from the intrinsic complexity in representing and processing 3D facial data. In this paper, we propose the intrinsic 3D facial sparse representation (I3DFSR) algorithm for multi-pose 3D face recognition. In this algorithm, each 3D facial surface is first mapped homeomorphically onto a 2D lattice, where the value at each site is the depth of the corresponding vertex on the 3D surface. Each 2D lattice is then interpolated and converted into a 2D facial attribute image. Next, the sparse representation is applied to those attribute images. Finally, the identity of each query face can be obtained by using the corresponding sparse coefficients. The innovation of our approach lies in the strategy of converting irregular 3D facial surfaces into regular 2D attribute images such that 3D face recognition problem can be solved by using the sparse representation of those attribute images. We compare the proposed algorithm to three widely used 3D face recognition algorithms in the GavabDB database, to six state-of-the-art algorithms in the FRGC2.0 database, and to three baseline algorithms in the NPU3D database. Our results show that the proposed I3DFSR algorithm can substantially improve the accuracy and efficiency of multi-pose 3D face recognition.     

Feature discovering for image classification via wavelet-like pattern decomposition

In this paper, we propose a feature discovering method incorporated with a wavelet-like pattern decomposition strategy to address the image classification problem. In each level, we design a discriminative feature discovering dictionary learning (DFDDL) model to exploit the representative visual samples from each class and further decompose the commonality and individuality visual patterns simultaneously. The representative samples reflect the discriminative visual cues per class, which are beneficial for the classification task. Furthermore, the commonality visual elements capture the communal visual patterns across all classes. Meanwhile, the class-specific discriminative information can be collected by the learned individuality visual elements. To further discover the more discriminative feature information from each class, we then integrate the DFDDL into a wavelet-like hierarchical architecture. Due to the designed hierarchical strategy, the discriminative power of feature representation can be promoted. In the experiment, the effectiveness of proposed method is verified on the challenging public datasets.     

Supervised within-class-similar discriminative dictionary learning for face recognition

The current study puts forward a supervised within-class-similar discriminative dictionary learning (SCDDL) algorithm for face recognition. Some popular discriminative dictionary learning schemes for recognition tasks always incorporate the linear classification error term into the objective function or make some discriminative restrictions on representation coefficients. In the presented SCDDL algorithm, we propose to directly restrict the representation coefficients to be similar within the same class and simultaneously include the linear classification error term in the supervised dictionary learning scheme to derive a more discriminative dictionary for face recognition. The experimental results on three large well-known face databases suggest that our approach can enhance the fisher ratio of representation coefficients when compared with several dictionary learning algorithms that incorporate linear classifiers. In addition, the learned discriminative dictionary, the large fisher ratio of representation coefficients and the simultaneously learned classifier can improve the recognition rate compared with some state-of-the-art dictionary learning algorithms.     

采用双字典协作稀疏表示的光照及表情顽健人脸识别

提出一种采用小波变换(WT)及双字典协作稀疏表示分类(CSRC)的人脸识别方法-WT-CSRC.WT-CSRC首先利用PCA(主成分分析)将小波分解后的人脸高频细节子图融合成高频细节图像;然后用PCA分别对人脸低频图像和高频细节图像进行特征提取,构造低频和高频特征空间,并用训练样本在两种特征空间上的投影集构造低频字典和高频字典;最后将测试样本在两种字典上进行稀疏表示,并引入互相关系数以增强人脸识别的可靠性,实现了人脸的协作分类.实验结果表明,提出的方法提高了人脸识别率,对光照变化及表情变化具有较强的顽健性,并且具有较高的时间效率.     

原子稀疏结合块结构稀疏的联合表示图像识别算法

针对结构稀疏表示识别算法中稀疏准则的选择以及字典内块的划分两个重要问题,提出两种改进的结构稀疏表示识别算法。首先,针对结构稀疏准则会出现较多系数不为零的情况,提出将结构稀疏准则与原子稀疏准则相结合的思路,包括并行和串行两种结合方式。并行结合是将两者以加权求和的方式同时作为稀疏表示的判别准则进行分类,串行结合则是在结构稀疏表示后,通过重组字典,再对测试样本进行原子稀疏表示实现分类。然后,针对字典中类内样本的块划分问题,提出基于MLP的结构稀疏表示识别算法,先将类内样本经过MLP的划分,保证各个分块分别位于低维的线性子空间中,再进行结构稀疏表示的分类。实验结果证明两种改进的结构稀疏表示识别算法的有效性。      

图约束字典和加权稀疏表示人脸超分辨率算法

针对低分辨率、低质量人脸图像重建问题,提出了一种新的基于稀疏表示的人脸超分辨率算法。在训练阶段,人脸的位置特征被用于保持人脸块的全局信息,人脸块间的几何结构被用于保持高低分辨率超完备冗余字典的流形结构,从而提高字典的表达能力;在重建阶段,K近邻加权稀疏表示被用于消除稀疏编码噪声,以提高高分辨率人脸图像重建系数的精度。实验结果表明,提出的方法取得了较好的主客观质量。     

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.     

Facial Expression Recognition through person-wise regeneration of expressions using Auxiliary Classifier Generative Adversarial Network (AC-GAN) based model

Recently, Facial Expression Recognition (FER) has gained much attention in the research area for its various applications. In the facial expression recognition task, subject-dependent issue is predominant when a small-scale database is used for training the system. The proposed Auxiliary Classifier Generative Adversarial Network (AC-GAN) based model regenerates ten expressions (angry, contempt, disgust, embarrassment, fear, joy, neutral, pride, sad, surprise) from input face image and recognizes its expression. To alleviate the subject dependence issue, we train the model person-wise and generate all the above expressions for a person and allow the discriminator to classify the expressions. The generator of our model uses U-Net Architecture, and the discriminator uses Capsule Networks for improved feature extraction. The model has been evaluated on the ADFES-BIV dataset yielding an overall classification accuracy of 93.4%. We also compared our model with the existing methods by evaluating our model on commonly used datasets like CK+, KDEF.     

基于小波字典稀疏表示的SAR图像目标识别

针对稀疏表示识别算法在图像域构造冗余字典时过分依赖预处理及原子维数较大的问题,提出基于小波字典的 SAR图像稀疏表示识别算法。首先采用二维离散小波变换将原始图像变换到小波域,建立小波域 SAR图像特征模型,得出小波域低频成分可充分表征目标类别信息的结论。然后取小波域低频成分进行2DPCA特征抽取构造小波字典,最后由改进 OMP 算法稀疏分解系数得到识别结果。SAR MSTAR数据的实验结果表明,在无预处理的情况下识别率高达99％,并且在含噪比10％的情况下识别率仍达96％。     

应用字典学习算法改善Bayer格式图像彩色恢复效果

利用单片探测器获取彩色图像,插值算法的优劣对结果起着决定性的作用。为了改善恢复效果,该文设计了一种基于字典学习的非线性Bayer格式图像彩色插值算法。根据图像梯度的变化,首先,在上下左右方向利用局部方向插值方法(LDI)对Bayer格式图像进行合并计算,用高斯混合模型(GMM)分类法训练字典,运用主分量分析(PCA)方法提取训练结果中的主要分量为学习提供样本,通过学习,得到R,B通道缺失的G^分量。然后,应用G^分量,插值得到另外两种缺失分量R^和B^,从而得到彩色图像。选取McMaster图像集作为字典,分别用算法对标准图像和使用DALSA公司彩色CMOS探测器开发的相机实际拍摄的图像进行插值恢复,较其它几种算法,视觉上伪彩色最少,峰值信噪比最优。整体性能优于现有的很多其它插值算法。     

基于主成分分析和字典学习的高光谱遥感图像去噪方法

高光谱图像变换域各波段图像噪声强度不同,并具有独特的结构。针对这些特点,该文提出一种基于主成分分析(Principal Component Analysis, PCA)和字典学习的高光谱遥感图像去噪新方法。首先,对高光谱数据进行PCA变换得到一组主成分图像;然后,对信息量较小的主成分图像分别采用基于自适应字典的稀疏表示方法和对偶树复小波变换方法去除空间维和光谱维的噪声;最后,通过PCA逆变换得出去噪后的数据。结合主成分分析和字典学习的优势,该文方法相对于传统方法对高光谱图像具有更好的自适应性,在细节得到保留的同时有效地抑制了斑块效应。对模拟和实际高光谱遥感图像的实验结果验证了该文方法的有效性。     

基于二次空间处理的联合稀疏表示高光谱图像分类

针对许多应用于高光谱图像分类的传统算法存在的分类精度低、光谱和空间信息利用不充分的问题,提出了一种基于二次空间处理的联合稀疏表示高光谱图像分类算法。在字典训练之前提取形态学特征,和光谱特征共同构建初始字典,以达到更快训练出较高质量的字典原子的目的。为了充分利用空间信息,首先通过超像素分割获取边缘信息,然后在超像素边缘和固定邻域双重约束下通过权值计算自适应选择邻域原子,实现空间信息的二次利用。在两个常用数据集上进行仿真实验,证明了本文所提算法可有效提升分类精度。      

基于字典优化的联合稀疏表示高光谱图像分类

针对训练样本量少导致高光谱图像分类精度低的问题,本文提出了一种基于字典优化的联合稀疏表示高光谱图像分类方法.首先,采取基于层次聚类的波段选择方法降低高光谱图像数据维度;其次,结合空间信息将高光谱数据划分为多个子集,利用已知标签信息的训练样本标记各个子集中可能成为训练样本的像元,组成训练样本备选集,根据光谱相似度准则筛选...