基于年龄流形的人脸图像年龄识别

人随着年龄的增长,外貌特征会发生相应的变化。而这种变化导致人脸识别率急剧下降,为此本文提出一种自动估计人脸年龄的方法,即利用流形学习方法从高维的人脸图像空间中的提取低维年龄流形作为人脸图像的年龄特征,然后利用支持向量回归方法构建全局年龄函数,最后用所得的年龄函数估计出未知人脸图像的年龄值。     

基于自适应本征维数估计流形学习的相空间重构降噪方法

针对实际工程领域振动信号噪声干扰大、具有强烈非线性等问题,提出了基于自适应本征维数估计流形学习的相空间重构降噪方法。利用相空间重构将一维含噪时间序列重构到高维相空间;基于极大似然估计法(maximum likelihood estimate,MLE)估计相空间中每个样本点的本征维数并使用自适应加权平均法计算全局本征维数;采用局部切空间排列(Local tangent space Alignment,LTSA)流形学习方法将含噪信号从高维相空间投影到有用信号的本征维空间中,剔除分布在高维空间中的噪声后,重构回一维时间序列。通过Lorenz仿真实验和风电机组振动信号降噪实例,证实了该方法具有良好的非线性降噪性能。     

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.     

基于核主元分析的头部姿势估计

现有头部姿势估计方法主要是基于几何分析和基于外现线性变换的方法,计算复杂、通用性不强.提出一种新的利用非线性的核变换算法进行姿势估计的方法,根据流形学习理论,不同姿势的高维人脸图像存在一低维流形结构,提取该流形结构可估计头部姿势.核主元分析是一种非线性降维算法,能够把这种流形结构嵌入到低维空间.利用核主元分析训练姿势估计曲线,然后把新图像投影到姿势曲线上,利用插值方法估计新投影点对应得姿势角度.核主元分析的方法克服了传统线性估计方法的缺点,实验证明该方法估计效果良好,并给出进一步提高估计效果的途径.     

基于三维模型的多姿态人脸识别

提出了一种利用三维人脸模型匹配二维人脸图像的分层人脸识别方法和基于模糊数学的人脸姿态角度估计算法.对多姿态二维图像进行姿态空间划分,利用主成分分析方法(PCA)形成多姿态特征脸.识别过程首先估计测试图像姿态和模糊姿态角,在估计的姿态空间内采用基于PCA的方法进行第一层识别得到候选个体,然后利用候选个体的三维模型结合模糊姿态角产生虚拟图像,利用相关进行第二层识别.实验结果表明,该方法对姿态的变化有较好的鲁棒性.     

基于小波分析的人脸图像处理

本文利用小波分析进行人脸图像处理,包括人脸图像的滤波、小波增强、以及人脸图像的小波分解等,为后续的特征提取和人脸识别打下良好的基础.实验结果表明,小波分解能够有效地降低人脸图像的维数,大大降低了后续处理算法的复杂度,减少了计算机的计算量.     

利用人眼分形码距离进行快速人脸识别

在利用人脸分形码距离进行识别时,需要大量的时间对人脸库中每张人脸图像进行迭代与距离运算.为克服这一缺点,本文提出了用水平方向高频子带来定位眼睛并将其从人脸中抽取出来,进一步提出了基于人眼分形码距离的人脸快速识别算法.利用该算法,可去掉大部分人眼分形码距离较大的图像,从识别时间复杂性分析,本文算法所需时间主要与人眼大小以及用于最后识别的图像数目有关.在ORL和YALE两个人脸库上的实验结果表明,与本征脸方法和直接利用人脸分形码距离方法比较,在用于最后识别的图像数目占人脸库中人脸总数的20%左右时,本文算法可使平均识别率保持在约90%,与其它方法基本持平.     

一种基于彩色+深度的人脸识别算法

本文提出了一种基于彩色+深度(RGB-D)的人脸识别方法,以提高识别率.首先从Kinect获得一个具有丰富的头部姿势变化、光照变化等不同条件下的彩色+深度(RGB-D)图像,将获取的同一个人在不同条件下的多个图像看做一个图像集;其次将Kinect获得的原始深度数据用于姿态估计和脸区域的自动裁剪.根据估计的姿态将一组脸部图像集分成多个子图像集.对于分类,本文提出了一种基于块的协方差矩阵表示图像模型在黎曼流形上一个子图像集的方法以降维,并使用SVM模型分别学习每个子图像集,然后将所有子图像集的结果相融合得出最终的识别结果.本文所提出的方法已经在包含不同条件下超过5 000幅RGB-D图像数据集中进行了评估.实验结果表明本文算法可实现高达98.84%的识别率.     

基于流形子带特征映射的转子复合故障特征提取方法

针对复合故障特征易被噪声信号淹没,传统时频分析和流形学习方法不能完整有效的挖掘故障潜在信息和进一步实现故障特征提取。在流形学习的基础上提出了一种流形子带思想并将其应用到转子复合故障特征提取研究中,进而得出了一种基于流形子带特征映射的转子复合故障特征提取方法。对故障原始信号序列进行相空间重构,结合小波包对噪声的强烈抑制性和对信号分辨率高的特点,将重构信号分解成不同频带即子带。将同故障多种工况下的同一频带融合成频带矩阵并估计其本征维数,并通过拉普拉斯特征映射算法以本征维数为依据将子带降维获取低维特征向量并提取信息熵,进一步实现故障特征提取。实验表明,相对于经典的局部线性嵌入和拉普拉斯特征映射等算法,流形子带特征映射算法不仅对单故障而且对复合故障特征进行了更完整有效的挖掘和提取。     

基于监督式等距映射的人脸和表情识别

提出了一种基于监督式等距映射的人脸和表情识别方法,该方法能同时完成身份和表情的识别.首先,运用监督式等距映射,将训练集中的人脸表情图像投影到低维流形空间,在这个流形空间里,图像的投影不仅实现了按其身份的分离,同时在同身份图像的内部,又实现了按其表情的聚类.然后,用非线性投影,将待测图像嵌入到流形空间.最后,采用加权knn分类器,识别出它的身份和表情.在Coln-Kanade和JAFFE人脸库上的实验表明,该方法对人脸和表情的识别的准确率比较高.     

Measuring the conformity of non‐simplicial elements to an anisotropic metric field

This paper extends an approach for measuring the element conformity of simplices to non‐simplicial elements of any type, in spaces of arbitrary dimension. Element non‐conformity is defined as the difference between a given size specification map, in the form of a Riemannian metric tensor, and the actual metric tensor of the element. An approach to the measurement of non‐conformity coefficients of non‐simplicial elements based on sub‐simplex division is proposed. An analysis of the measure's behaviour presented for quadrilaterals, hexahedra, prisms and pyramids shows that the measure is sensitive to size, stretching and orientation variations, as well as to other types of element shape degeneration. Finally, numerical applications show that the metric conformity measure can be used as a quality measure to quantify the discrepancy between a whole non‐simplicial mesh and a complex anisotropic size specification map. Copyright © 2005 John Wiley & Sons, Ltd.     

3D model-based pose invariant face recognition from multiple views

A 3D model-based pose invariant face recognition method that can recognise a human face from its multiple views is proposed. First, pose estimation and 3D face model adaptation are achieved by means of a three-layer linear iterative process. Frontal view face images are synthesised using the estimated 3D models and poses. Then the discriminant `waveletfaces' are extracted from these synthesised frontal view images. Finally, corresponding nearest feature space classifier is implemented. Experimental results show that the proposed method can recognise faces under variable poses with good accuracy     

基于肤色特征和动态聚类的彩色人脸检测

在人类视觉机制和肤色聚类特性的基础上,提出了一种复杂背景下人脸检测方法。该方法采用K-均值动态聚类分析算法,利用人类肤色特征在输入图像中检测包含人脸的似人脸区作为候选人脸,再用同样的方法对候选人脸区域进行扫描,得到真正的人脸。实验结果表明,该方法的正确检出率达到84%,受背景、光照、角度、姿态的影响很小,具有较好的鲁棒性。     

Face Age Estimation Based on CSLBP and Lightweight Convolutional Neural Network

As the use of facial attributes continues to expand, research into facial age estimation is also developing. Because face images are easily affected by factors including illumination and occlusion, the age estimation of faces is a challenging process. This paper proposes a face age estimation algorithm based on lightweight convolutional neural network in view of the complexity of the environment and the limitations of device computing ability. Improving face age estimation based on Soft Stagewise Regression Network (SSR-Net) and facial images, this paper employs the Center Symmetric Local Binary Pattern (CSLBP) method to obtain the feature image and then combines the face image and the feature image as network input data. Adding feature images to the convolutional neural network can improve the accuracy as well as increase the network model robustness. The experimental results on IMDB-WIKI and MORPH 2 datasets show that the lightweight convolutional neural network method proposed in this paper reduces model complexity and increases the accuracy of face age estimations.     

Fast Near-duplicate Image Detection in Riemannian Space by A Novel Hashing Scheme

There is a steep increase in data encoded as symmetric positive definite (SPD) matrix in the past decade. The set of SPD matrices forms a Riemannian manifold that constitutes a half convex cone in the vector space of matrices, which we sometimes call SPD manifold. One of the fundamental problems in the application of SPD manifold is to find the nearest neighbor of a queried SPD matrix. Hashing is a popular method that can be used for the nearest neighbor search. However, hashing cannot be directly applied to SPD manifold due to its non-Euclidean intrinsic geometry. Inspired by the idea of kernel trick, a new hashing scheme for SPD manifold by random projection and quantization in expanded data space is proposed in this paper. Experimental results in large scale near-duplicate image detection show the effectiveness and efficiency of the proposed method     

盲源分离用于DOA估计研究

方位估计是水下目标定位、跟踪的前提。提出了一种复数域奇异值分解盲源分离方法,估计出了阵列流形,并利用阵列流形表现出的相位关系完成了目标方位估计。通过仿真实验与MUSIC高分辨方位估计方法和相关文献的方法进行了对比,结果表明该方法能很好地实现目标方位的实时估计,且性能更佳。     

基于肤色的人脸检测

提出一种基于肤色信息的正面人脸检测方法。设计了基于颜色的皮肤分类器，对图像中的皮肤区域和非皮肤区域进行分割；并对分割出的皮肤区域进行预处理，初步确定候选人脸；再进一步将候选脸与模板脸进行匹配最终确定是否为人脸，并给出检测到的人脸的位置信息。对各类型图像进行大量实验表明，本方法具有较好的准确性和实用性。     

基于Gabor脸和隐马尔可夫模型的人像识别算法

提出了基于Gabor小波变换和隐马尔可夫模型的人像识别算法。该算法先对人脸图像进行多分辨率的Gabor小波变换,采用主元分析法对每个结点进行降维,最后形成Gabor脸。把Gabor脸的每个特征结作为观测向量,对隐马尔可夫模型进行了训练,并把优化的模型参数用于人脸识别。实验结果表明,本文方法识别率高,复杂度较低,对部分遮挡的图像具有较大的容忍度。     

3D Head Pose Estimation through Facial Features and Deep Convolutional Neural Networks

Face image analysis is one among several important cues in computer vision. Over the last five decades, methods for face analysis have received immense attention due to large scale applications in various face analysis tasks. Face parsing strongly benefits various human face image analysis tasks inducing face pose estimation. In this paper we propose a 3D head pose estimation framework developed through a prior end to end deep face parsing model. We have developed an end to end face parts segmentation framework through deep convolutional neural networks (DCNNs). For training a deep face parts parsing model, we label face images for seven different classes, including eyes, brows, nose, hair, mouth, skin, and back. We extract features from gray scale images by using DCNNs. We train a classifier using the extracted features. We use the probabilistic classification method to produce gray scale images in the form of probability maps for each dense semantic class. We use a next stage of DCNNs and extract features from grayscale images created as probability maps during the segmentation phase. We assess the performance of our newly proposed model on four standard head pose datasets, including Pointing’04, Annotated Facial Landmarks in the Wild (AFLW), Boston University (BU), and ICT-3DHP, obtaining superior results as compared to previous results.