基于自适应LBP人脸识别的身份验证

提出了一种自适应LBP人脸识别算法用于进行身份认证。在身份特征录入阶段,首先采用Harr人脸级联分类器对人脸样本库进行人脸区域检测,并使用PCA方法对人脸区域进行降维处理;然后通过LBP二值模式的人脸识别算法提取人脸样本的特征值;最后通过LBP人脸训练生成人脸数据特征库。通过多场景人脸图像库和阈值队列,通过多阈值全组人脸匹配,建立人脸阈值特征库。在身份验证阶段,将登录用户人脸与人脸阈值特征库做粗粒度人脸LBP直方图匹配,确定当前最优的LBP阈值;然后将登录用户人脸与人脸数据特征库做LBP直方图匹配,通过匹配结果确定登录用户的系统权限。实验结果表明,在图像和视频模式下,基于自适应LBP人脸识别算法的身份验证具有很高的鲁棒性。     

基于视频监控的人脸识别方法

目前人脸识别方法主要针对静态图像进行识别,而在监控视频中,不同视频帧人脸具有相关性且只有部分人脸能够有效反映人脸信息。根据监控视频中人脸图像变化特性,提出了一种基于监控视频的人脸识别方法。首先通过结合人脸检测与跟踪技术获得视频人脸序列,然后以视频人脸序列中部分人脸图像识别结果为导向选取全部人脸序列图像中的代表人脸图像进行识别,最后根据选取的全部人脸图像识别结果综合反映人脸信息。实验结果表明,该方法能够在确保识别率和误识率的前提下有效提升监控视频中人脸识别的实时性。     

基于SVM的人脸精确验证

人脸检测系统包括了人脸检测粗筛选和人脸精确验证两个阶段,人脸精确验证是在人脸检测粗筛选的基础上所做的工作,目的是通过精确验证去除粗筛选阶段所得到的候选区域中的非人脸部分.精确验证阶段采用了线性鼻子SVM分类器和非线性特征脸SVM分类器相结合的策略.实验结果表明,这种精确验证的方法基本上可以精确地检验出粗筛选阶段所得图片中的人脸区域.     

Mask guided diverse face image synthesis

Recent studies have shown remarkable success in face image generation task. However, existing approaches have limited diversity, quality and controllability in generating results. To address these issues, we propose a novel end-to-end learning framework to generate diverse, realistic and controllable face images guided by face masks. The face mask provides a good geometric constraint for a face by specifying the size and location of different components of the face, such as eyes, nose and mouse. The framework consists of four components: style encoder, style decoder, generator and discriminator. The style encoder generates a style code which represents the style of the result face; the generator translate the input face mask into a real face based on the style code; the style decoder learns to reconstruct the style code from the generated face image; and the discriminator classifies an input face image as real or fake. With the style code, the proposed model can generate different face images matching the input face mask, and by manipulating the face mask, we can finely control the generated face image. We empirically demonstrate the effectiveness of our approach on mask guided face image synthesis task.     

基于深度学习的轻量级和多姿态人脸识别方法

目前基于深度学习的人脸识别方法存在识别模型参数量大、特征提取速度慢的问题,而且现有人脸数据集姿态单一,在实际人脸识别任务中无法取得好的识别效果。针对这一问题建立了一种多姿态人脸数据集,并提出了一种轻量级的多姿态人脸识别方法。首先,使用多任务级联卷积神经网络（MTCNN）算法进行人脸检测,并且使用MTCNN最后包含的高层特征做人脸跟踪;然后,根据检测到的人脸关键点位置来判断人脸姿态,通过损失函数为ArcFace的神经网络提取当前人脸特征,并将当前人脸特征与相应姿态的人脸数据库中的人脸特征比对得到人脸识别结果。实验结果表明,提出方法在多姿态人脸数据集上准确率为96.25%,相较于单一姿态的人脸数据集,准确率提升了2.67%,所提方法能够有效提高识别准确率。     

基于KLT和BFGS的人脸姿态估计

在对给定的人脸图像序列准确提取正面人脸特征点后,利用改进的KLT方法跟踪非正面人脸图像的特征点。根据人脸形状特性,使用人脸的多个特征点作为人脸模型。在近似估计人脸姿态后,以改进的BFGS算法精确估计3D人脸空间姿态。实验结果证明,该方法可以获得唯一的3D人脸空间姿态,相比同类方法有更好的姿态估计精确度。     

稀疏表示和支持向量机相融合的非理想环境人脸识别

当前的人脸识别算法在理想环境下的识别正确率高,自适应能力强;但是在非理想环境下,人脸识别正确率急剧下降。为了提高人脸识别结果的稳定性,设计了稀疏表示和支持向量机相融合的非理想环境人脸识别算法。首先,提取非理想环境人脸的特征,并构建非理想环境人脸识别的特征字典;然后,采用特征字典对非理想环境人脸识别训练样本和测试样本进行处理,构建非理想环境人脸识别的学习样本;最后,采用支持向量机建立非理想环境人脸识别的分类器来对非理想环境人脸进行识别,并采用多个标准人脸数据库对所提非理想环境人脸识别算法进行测试。文中算法的非理想环境人脸识别正确率高,误识率和拒识率低,相对于其他人脸识别算法,其更适应环境的变化,对非理想环境人脸识别的整体效果更优,而且提高了非理想环境人脸识别的效率,具有十分明显的优越性。     

3D通用人脸模型的自适应算法及应用

利用3D人脸建模的方法进行人脸识别有效地克服了2D人脸识别系统中识别率易受光照、姿态、表情影响的缺陷。文章采用一种依据人脸图像对3D通用人脸模型进行自适应调整的有效算法,构造出特定的人脸模型并运用于人脸识别中。通过比较从人脸图像中估算出的特征点与通用人脸模型在图像平面上的投影点之间的关系,对3D通用人脸模型进行全局和局部调整,以适应人脸中眼、口、鼻的个性化特征。最后以一个实例说明了此算法的应用。     

基于新Haar-like特征的多角度人脸检测

在Haar-like特征的基础上增加新的检测特征,给出特征计算方法和积分方法,实现多角度人脸检测。将多角度人脸分为3类,即全侧脸、半侧脸和正面人脸。利用连续Adaboost算法训练各类人脸检测器,用金字塔式结构将各类人脸检测器级联成一个多角度人脸检测器。在CMU人脸检测集合上,该检测器的成功率为85．2％,高于Adaboost算法和浮点Adaboost算法。     

灰度图像中基于像素分布特征的人脸定位

提出了一种利用人脸图像的像素分布特征来定位人脸的方法，在定位人脸的内轮廓时利用了图像二值化后的分布特征和灰度图的像素分布特征相结合的方法，然后将人脸区域的图像进行标准化，经过以脸图像可以方便地用于人脸的识别。在对采集到的图像进行的测试中得到了较好的效果。     

Real-time face tracking and recognition using the mobile robots

The terrain is complex and dynamic in a disaster. This paper aimed at constructing a multipose-specific feature model for online face recognition and tracking in a search and rescue operation. This paper proposes an integrated multipose face tracking and recognition system mounted on an unmanned aerial vehicle (UAV). The face model is constructed online by multi-scale block local binary pattern (MB-LBP) for face recognition. The generic and specific face models are further integrated for face tracking. Mechanisms for the online update of face models to retrieve loss of face tracking are also implemented. The results show that the proposed system achieves stable and robust tracking despite uncertainties (e.g. non-rigid human face, face expression changes, different face poses, complex background, varying illumination, partial visual occlusion, and pose changes). The target loss during tracking can be retrieved correctly. In face recognition, the multipose-specific face model can achieve an accuracy (above 70%). The results demonstrate the feasibility of the proof-of-concept using UAV or ground mobile robot (GMR) for real-time face recognition and tracking.     

人物脸部图片的修改与实现*

包括人脸表情修改在内的人体生物特征的操作技术,涉及的脸部图像处理是图像处理学科的技术难点.研究了影响人脸识别技术实用化的一些因素,提出了开发人脸识别与修改技术的方法,开发出一个人脸图像处理系统,主要用于图片中人脸部位的变换与修改,为今后开发性能优良的人脸识别与修改系统奠定基础.     

人脸识别技术

人脸图像的易取性和人脸变化的多样性使人脸识别研究更富有挑战性.按照人脸检测、特征提取和识别3个关键过程,分别对基于二维和三维人脸信息的人脸识别技术和方法进行了详细的阐述;展望了人脸识别研究的趋势,并提出了可能取得突破性研究进展的研究途径.     

一种个性化人脸三维建模方法

描述了一种特定人的人脸三维建模方法,该方法用该人的正面及侧面人脸两张照片,通过选择关键特征点,在基本人脸模型基础上,经过变形,得到特定人脸三维网格模型。再经纹理匹配,获得特定人的三维人脸模型。该方法已在微型计算机上进行了模拟,并成功地获得酷似真人的人脸三维模型。     

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.     

Image-based face illumination transferring using logarithmic total variation models

In this paper, we present a novel image-based technique that transfers illumination from a source face image to a target face image based on the Logarithmic Total Variation (LTV) model. Our method does not require any prior information regarding the lighting conditions or the 3D geometries of the underlying faces. We first use a Radial Basis Functions (RBFs)-based deformation technique to align key facial features of the reference 2D face with those of the target face. Then, we employ the LTV model to factorize each of the two aligned face images to an illumination-dependent component and an illumination-invariant component. Finally, illumination transferring is achieved by replacing the illumination-dependent component of the target face by that of the reference face. We tested our technique on numerous grayscale and color face images from various face datasets including the Yale face Database, as well as the application of illumination-preserved face coloring.     

头部多角度人脸快速跟踪算法DSP实现

针对传统驾驶员疲劳检测人脸跟踪算法复杂,DSP实现时实时性不强,不能有效地实现多角度人脸跟踪的问题,提出了一种快速人脸跟踪算法.该算法通过对YCbCr肤色模型进行图像预处理、肤色检测,提取人脸区域,通过对亮度信号Y进行统计运算,判断人脸边界,再进行相似度判断,从而实现人脸区域的跟踪.实验结果表明,该方法简单、鲁棒性强,能够快速地实现彩色图像人脸多角度跟踪.     

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.     

基于特征脸的人脸识别系统的研究

人脸识别技术是通过分析人脸图像,并从人脸图像中提取有效的识别信息,用来辨认身份的一门技术.文章阐述了基于特征脸的人脸识别的基本算法,并对该方法进行改进,最后对其进行了仿真.该方法主要通过求出人脸图象与数据库中的特征脸空间距离来进行人脸的识别和分类,做到了快速准确地识别人脸.     

一种改进的CAMShift跟踪算法及人脸检测框架

为充分利用人脸视频图像序列中的时空信息,获得更加准确的人脸比对图像序列,提出一种结合人脸跟踪的人脸检测框架。使用简单快速的正面人脸检测算法对人脸视频图像序列进行检测,用检测的结果对人脸跟踪算法进行初始化及校验和调整。为解决CAMShift跟踪算法容易受类肤色区域影响而导致提取到的人脸区域存在冗余信息的问题,提出一种改进的CAMShift-KLT算法。该算法利用兴趣点跟踪人脸图像的边缘,达到准确获取人脸比对图像的目的。实验结果表明,与CAMShift算法相比,CAMShift-KLT算法获取的人脸区域更精准,同时具有较小的跟踪偏移距离、较大的跟踪命中率和更高的跟踪有效性。与对比算法相比,CAMShift-KLT算法能够获得与理想的人脸区域更加一致的跟踪区域。