基于二维图像矩阵的ICA人脸识别

为了解决传统独立分量分析(ICA)在人脸识别过程中存在的高维小样本问题,同时为了提高识别效率,提出了一种基于二维图像矩阵的独立分量分析(ICA)特征提取方法.该方法将人脸图像矩阵作为训练样本,首先利用主分量分析(PCA)对训练样本进行去二阶相关和降维处理,然后对处理后的样本进行ICA特征提取,由于训练样本维数很小,因此它降低了传统ICA方法中高维小样本问题产生的识别错误率,同时减少了识别时间.在Yale人脸库和ORL人脸库上验证了该算法的有效性.     

基于小波变换、二维主元分析与独立元分析的人脸识别方法

结合小波变换(WT)、二维主元分析(2DPCA)和独立元分析(ICA)的特点,提出一种人脸识别方法.首先,利用小波变换将原始图像分解为高频分量和低频分量,并忽略水平高频与垂直高频分量,从而消除噪声.然后,通过2DPCA对该图像进行降维,求得白化矩阵.再利用ICA获得训练样本的独立元成分,同时求得训练样本独立基构造的独立基子空间.最后,将训练样本与测试样本分别朝该独立基子空间投影,获得样本的投影特征,并依据最近邻准则完成人脸识别.基于ORL与Yale人脸数据库的实验结果表明,本文方法正确识别率高于2DPCA、2DPCA-ICA与WT-2DPCA算法.     

基于分块独立分量分析的人脸识别

提出了一种基于分块独立分量分析(BICA)的特征提取方法。该方法通过将人脸分块降低了光照条件、人脸表情等外在因素对人脸识别的影响,并先后将分块后重组的矩阵的行和列作为训练样本提取独立分量,由于训练样本维数很小,因此它降低了传统独立分量分析（ICA）方法中存在的高维小样本问题产生的识别错误率,同时减少了识别时间。在Yale人脸库和AR人脸库上验证了该算法的有效性。     

一种新的多人脸检测方法研究

自动人脸检测是人脸识别系统的一个重要部分,本文提出了一种新的基于独立成分分析（ICA）和多项式神经网络（PNN）相结合的人脸检测方法,该方法首先在训练样本中使用ICA分离出代表人脸和非人脸特征子空间的独立影像基,把训练图像映射到该子空间降维后作为PNN网络的输入训练网络;对测试图像采用移动多尺度窗口提取图像模式,采用ICA降维后输入PNN网络,进而分类检测出人脸和非人脸。算法通过CMU-MIT的复杂背景人脸库中的多人脸图像进行实验,得到很高的检测率和较低的误检率.     

基于MW(2D)~2 PCA的单训练样本人脸识别

传统的人脸识别方法在单训练样本条件下性能会急剧下降,因此,研究出适合于单样本情况下的识别算法是人脸识别问题面临的巨大挑战.针对两个方向的二维主成分分析((2D)~2PCA)算法进行改进,文中提出将加权和分块与(2D)~2PCA相结合的方法称为分块加权(2D)~2PCA,以便更有效地提取人脸的局部特征.同时把模糊理论引入分类决策,应用于单训练样本人脸识别问题.在ORL人脸库以及部分CAS-PEAL人脸库中的实验结果表明,文中方法能取得较好的识别效果.     

基于独立分量分析和遗传算法的人脸性别分类

性别是人脸反映的一个重要信息,通过人脸图像实现性别自动分类对大型人脸数据库的检索和识别具有重要意义。提出了一种新的结合独立分量分析(ICA)和遗传算法(GA)的人脸性别分类方法。首先采用快速独立分量分析方法(FastICA)提取人脸图像的独立基图像和投影向量,获得人脸的低维表征;然后通过遗传算法从该低维空间中选择对性别分类有利的特征子集;最后采用支持向量机进行分类。将ICA的空间局部特征提取功能、遗传算法快速寻优的特征选择功能以及SVM的强分类能力有机地结合起来。实验表明,该方法取得了很好的分类性能。     

基于独立分量分析的人脸超分辨率重建

提出一种基于独立分量分析(ICA)的人脸超分辨率重建算法。该算法利用ICA从高分辨率训练图像中提取出独立分量,并对ICA系数进行先验估计。对于给定的低分辨率图像,结合最大后验概率估计求出ICA系数,进行ICA反变换得到高分辨率图像的近似估计,并利用局部结构张量对图像进行精化处理得到重建图像。仿真结果表明,该算法在实现人脸超分辨率重建的同时保持了人脸整体结构特征,且对光照、表情、姿态等具有一定的鲁棒性,将重建结果用于人脸辨识,有效提高了辨识效率。     

基于HOG多特征融合与随机森林的人脸识别

针对人脸识别在复杂环境下识别率低的问题,提出了一种基于梯度直方图(HOG)多特征融合与随机森林的人脸识别方法.该方法通过HOG特征描述子对人脸进行特征提取.首先以网格作为采样窗在整个人脸图上进行整体HOG特征的提取,并将人脸图像分成均匀子块,在包含有人脸关键部分的子块中提取局部HOG特征.然后通过二维主成分分析(2DPCA)和线性判别分析(LDA)对整体和局部特征进行降维,并进行特征层融合形成最终分类特征,最后通过随机森林分类器对其进行分类.FERET人脸库、CAS-PEAL-R1人脸库、真实场景人脸库实验表明,该方法对光照具有鲁棒性,且有较高的识别率和较短的识别时间.     

增强的无监督人脸鉴别技术

增强的独立分量分析（EICA）是一种基于样本整体特征的无监督特征抽取方法,并没有考虑样本的局部特征,因此EICA不利于处理人脸识别这类非线性问题的。无监督鉴别投影技术（UDP）用于高维数据压缩,其基本思想是寻找一组有效的投影方向,使得样本投影后,局部散度最小同时非局部散度最大。UDP同时考虑到样本的局部特征和非局部特征,能够反映样本内在的数据关系,因此UDP能够对样本有效地分类。提出了一种增强的无监督人脸鉴别技术,该方法结合了EICA和UDP的优点,能够：（1）反映样本高阶统计特征;（2）发掘样本内在的几何结构,从而有利于分类。在Yale人脸库和FERET人脸库上的实验验证了该算法的有效性。     

基于改进的独立分量分析的人脸识别方法

将独立分量分析（Independent Component Analysis，ICA）作为人脸特征提取方法。ICA所提取的特征分类能力强、相互独立，对像素间高阶统计特性敏感，并且不易受光照变化的影响。实验结果表明，基于IcA的人脸特征提取方法的识别性能优于特征脸法。针对传统的ICA算法（Informax算法）存在迭代次数多，难收敛，并且需要人工设定步长来调整学习速度的不足，本文采用FastICA作为ICA的快速算法，并将其关键迭代步骤加以改进，减少了耗时的雅可比矩阵求逆的运算次数。所提出的改进的FastICA具有无需人工参与，收敛速度快，迭代次数少的优点。在特征选择方面，本文将遗传算法（Genetie Algorithm，GA）应用到独立分量的选择与优化中，从而在保证较高识别性能的前提下，获得最优的人脸特征子集。     

2D face fitting-assisted 3D face reconstruction for pose-robust face recognition

Recent face recognition algorithm can achieve high accuracy when the tested face samples are frontal. However, when the face pose changes largely, the performance of existing methods drop drastically. Efforts on pose-robust face recognition are highly desirable, especially when each face class has only one frontal training sample. In this study, we propose a 2D face fitting-assisted 3D face reconstruction algorithm that aims at recognizing faces of different poses when each face class has only one frontal training sample. For each frontal training sample, a 3D face is reconstructed by optimizing the parameters of 3D morphable model (3DMM). By rotating the reconstructed 3D face to different views, pose virtual face images are generated to enlarge the training set of face recognition. Different from the conventional 3D face reconstruction methods, the proposed algorithm utilizes automatic 2D face fitting to assist 3D face reconstruction. We automatically locate 88 sparse points of the frontal face by 2D face-fitting algorithm. Such 2D face-fitting algorithm is so-called Random Forest Embedded Active Shape Model, which embeds random forest learning into the framework of Active Shape Model. Results of 2D face fitting are added to the 3D face reconstruction objective function as shape constraints. The optimization objective energy function takes not only image intensity, but also 2D fitting results into account. Shape and texture parameters of 3DMM are thus estimated by fitting the 3DMM to the 2D frontal face sample, which is a non-linear optimization problem. We experiment the proposed method on the publicly available CMUPIE database, which includes faces viewed from 11 different poses, and the results show that the proposed method is effective and the face recognition results toward pose variants are promising.     

Efficient face candidates selector for face detection

In this paper an efficient face candidates selector is proposed for face detection tasks in still gray level images. The proposed method acts as a selective attentional mechanism. Eye-analogue segments at a given scale are discovered by finding regions which are roughly as large as real eyes and are darker than their neighborhoods. Then a pair of eye-analogue segments are hypothesized to be eyes in a face and combined into a face candidate if their placement is consistent with the anthropological characteristic of human eyes. The proposed method is robust in that it can deal with illumination changes and moderate rotations. A subset of the FERET data set and the BioID face database are used to evaluate the proposed method. The proposed face candidates selector is successful in 98.75% and 98.6% cases, respectively.     

基于人脸认知模式的相似脸搜索

目的 人类对人脸认知模式的探索由来已久,并且已经成功应用于美容整形等研究领域。然而,目前在计算机视觉和模式识别领域,计算人脸相似度的方法没有考虑人对人脸的认知模式,使得现有方法的计算结果从人的认知习惯角度来讲并非最佳。为克服以上缺陷,提出一种基于人脸认知模式的相似脸搜索算法。方法 依据人脸认知模式,选取特征点,并计算特征量,构造各面部器官（眼睛、鼻子、嘴巴、脸型）分类模型,即面部器官形状相似性度量模型,并采用圆形LBP算子,计算两幅人脸对应器官的纹理相似度,二者综合作为相似脸搜索的依据。结果 分别用本文方法和代表相似脸搜索最高水平的Face++的方法对80幅正面、中性表情、平视角度拍摄的人脸图像进行测试。本文方法的整体准确率高于Face++方法,其中,TOP1、TOP2最相似搜索结果准确率优势明显,均高出Face++方法12%以上。结论 实验结果表明,本文方法的搜索结果更加符合人脸认知模式,可应用于正面、中性表情、平视角度拍摄的人脸图像的相似脸搜索。此外,还可以将此类基于认知模式的图像搜索思路推广应用于商业领域,如基于图像的相似网购商品搜索等。     

人脸识别活体检测研究方法综述

人脸识别具有广泛的应用,但容易受到伪造的欺骗人脸攻击而影响安全性,设计检测准确率高、泛化能力强、满足实时性需求的活体检测方法是目前的研究重点。将现有的人脸活体检测研究方法分为基于手工设计特征表达、基于深度学习和基于融合策略的方法,介绍每类方法所包含的典型算法的基本思想、实现步骤及优缺点。最后对已公开的人脸活体检测数据库进行整理说明,对人脸活体检测的发展趋势以及还需要进一步解决的问题进行综述,为今后人脸活体检测的研究提供参考和借鉴。     

Bimode model for face recognition and face representation

Tensorface based approaches decompose an image into its constituent factors (i.e., person, lighting, viewpoint, etc.), and then utilize these factor spaces for recognition. However, tensorface is not a preferable choice, because of the complexity of its multimode. In addition, a single mode space, except the person-space, could not be used for recognition directly. From the viewpoint of practical application, we propose a bimode model for face recognition and face representation. This new model can be treated as a simplified model representation of tensorface. However, their respective algorithms for training are completely different, due to their different definitions of subspaces. Thanks to its simpler model form, the proposed model requires less iteration times in the process of training and testing. Moreover bimode model can be further applied to an image reconstruction and image synthesis via an example image. Comprehensive experiments on three face image databases (PEAL, YaleB frontal and Weizmann) validate the effectiveness of the proposed new model.     

基于人脸超分的网络视频人脸检测

针对网络视频质量低导致人脸检测准确率低的问题,提出一种基于人脸超分辨率重建的SR Face Detection模型.使用去掉自监督分支且以Resnet50为基础网络的RetinaFace进行帧图片人脸的粗提取;在人脸检测器后增加一个人脸超分辨率重建网络,剔除粗提取人脸中的非人脸.该超分网络的生成网络使用残差密集块进行特征提取,加入注意力损失和热图,更好地还原面部细节;根据实际需求设计一个多判别功能的判别网络.实验结果表明,SR Face Detection模型在WID-ER FACE数据集上取得了令人信服的结果,提高了人脸检测准确率,且人脸检测场景越复杂,效果提升越明显.     

Automatical detection of face features and exact face contour

The approach based on the mathematical morphology and the variational calculus is presented for the detection of an exact face contour in still grayscale images. The facial features (eyes and lips) are detected by using the mathematical morphology and the heuristic rules. Using these features an image is filtered and an edge map is prepared. The face contour is detected by minimizing its internal and external energy. The internal energy is defined by the contour tension and the rigidity. The external energy is defined by using the generalized gradient vector flow field of the image edge map. Initial contour is calculated using the detected face features. The contour detection experiments were performed using the database of 427 face images. Automatically detected contours were compared with manually labeled contours using an area and the Euclidean distance-based error measures.     

改进人脸特征矫正网络的遮挡人脸识别方法

现有人脸识别模型受口罩等遮挡因素影响导致准确率无法提升。当前主流研究方法将有无遮挡场景分开训练后,整合应用于多场景。针对遮挡人脸识别模型的局限性,提出一种改进人脸特征矫正网络（FFR-Net）模型。该模型可同时用于有无遮挡人脸识别并应用于口罩与眼镜遮挡两种识别场景中。人脸特征矫正网络模型提出了一种人脸特征矫正模块,为保证充分利用无遮挡区域特征信息,在该模块中的空间分支引入involution算子扩大图像信息交互区域,增强在空间范围内面部特征信息;在通道分支引入坐标注意力机制,捕获跨通道信息以增强特征表示,利于模型准确地定位识别目标区域;将Meta-ACON作为该模块新的动态激活函数,通过动态调整线性或非线性程度以提高模型泛化能力和计算准确度。最后,利用改进的人脸特征矫正网络模型在CASIA-Webface经处理的有无口罩遮挡人脸数据集上进行训练,其在LFW经处理的有无口罩遮挡数据集、Meglass数据集上的测试结果准确率分别达到了82.50%和89.75%,优于现有算法,验证了所提方法的有效性。     

Benchmarking lightweight face architectures on specific face recognition scenarios

Artificial Intelligence Review - This paper studies the impact of lightweight face models on real applications. Lightweight architectures proposed for face recognition are analyzed and evaluated on...     

Greedy face routing with face identification support in wireless networks

Geographic face routing protocols planarize the connectivity graph of a wireless network in a distributed manner and forward packets on the resulted planar topology with high reliability and low overhead. A preferable face routing protocol should provide both guaranteed packet delivery and efficient routing paths, which requires a flexible face switch algorithm adaptive to the network complexity. In this paper, we present a new face routing algorithm named GFRIS that offers both features by performing active probe to measure the face size and generate a unique face identification sequence – face ID. In GFRIS, face switch occurs only if the outgoing edge intersects the local minimum-destination line at a progressive location and the crossing edge is shared between two different faces. To avoid the severe performance penalty when an inefficient face traversal direction is selected on large faces, GFRIS uses the face size to trigger the bounded face traversal procedure as proposed earlier in GOAFR+. As multiple local minimum locations on a face will trigger bounded search repetitively, GFRIS employs a fast forward mode to bypass bidirectional search on the face, which leads to significantly improved path stretch performance. This paper provides a detailed performance comparison between GFRIS and the existing face routing algorithms including GFG, GPSR, GOAFR+ and GFG2. Simulation results show that, by using face ID to assist face switch and adaptively applying the normal and bounded face traversal rules according to the face size, GFRIS can achieve better routing efficiency with low control overhead compared to other protocols evaluated across a wide node density range.