Matching pursuit filters applied to face identification

We present a face identification algorithm that automatically processes an unknown image by locating and identifying the face. The heart of the algorithm is the use of pursuit filters. A matching pursuit filter is an adapted wavelet expansion, where the expansion is adapted to both the data and the pattern recognition problem being addressed. For identification, the filters find the features that differentiate among faces, whereas, for detection, the filters encode the similarities among faces. The filters are designed though a simultaneous decomposition of a training set into a two-dimensional (2-D) wavelet expansion. This yields a representation that is explicitly 2-D and encodes information locally. The algorithm uses coarse to fine processing to locate a small set of key facial features, which are restricted to the nose and eye regions of the Face. The result is an algorithm that is robust to variations in facial expression, hair style, and the surrounding environment. Based on the locations of the facial features, the identification module searches the data base for the identity of the unknown face using matching pursuit filters to make the identification. The algorithm was demonstrated on three sets of images. The first set was images from the FERET data base. The second set was infrared and visible images of the same people. This demonstration was done to compare performance on infrared and visible images individually, and on fusing the results from both modalities. The third set was mugshot data from a law enforcement application.     

使用部件信息改进弹性匹配人脸识别

提出了一种综合利用部件信息和整体信息的人脸识别算法。利用部件定位得出人脸关键点（例如暗孔和鼻尖）的位置，然后利用这些关键点信息来限制弹性匹配的搜索范围。实验结果表明，这种方法在很大地提高了识别速度的同时能使识别率保持不变甚至还有所提高。     

Robust facial landmarking for registration

Finding landmark positions on facial images is an important step in face registration and normalization, for both 2D and 3D face recognition. In this paper, we inspect shortcomings of existing approaches in the literature and compare several methods for performing automatic landmarking on near-frontal faces in different scales. Two novel methods have been employed to analyze facial features in coarse and fine scales successively. The first method uses a mixture of factor analyzers to learn Gabor filter outputs on a coarse scale. The second method is a template matching of block-based Discrete Cosine Transform (DCT) features. In addition, a structural analysis subsystem is proposed that can determine false matches, and correct their positions.     

基于稀疏RAM的逼近型神经网络与统计模式识别的人脸识别

本文提出了一种基于稀疏RAM的逼近型神经网络(SN-tuple)与统计模式识别相结合的人脸识别方法,采用首先直接将原始图像数据输入稀疏RAM的逼近型神经网络中进行粗分类,再由统计模式识别方法中的PCA、LDA来进行最终细分类的方法,通过大量的实验证明了该方法的有效性。     

人脸识别研究进展

人脸识别技术在各种应用的推动下发展很快。而近几年中，为避免各种实际应用环境的限制，非约束环境下的人脸识别也得到了很大的发展。本文概述了人脸识别的一些主要方法，讨论了影响人脸识别的几个主要因素及其处理方法以及基于视频的人脸识别技术，最后指出了鲁棒的人脸识别技术的研究方向和发展前景。     

人脸识别方法的综述

人脸识别技术是利用计算机分析人脸图像,从中提取有效的特征信息,用来辨认身份的一门技术。在此简单介绍了近年来常用的几种人脸识别方法,如：特征脸、隐马尔科夫、神经网络、以及弹性图匹配方法等。     

基于深度卷积网络的3D人脸重构算法

基于单张人脸图片的3D人脸模型重构,无论是在计算机图形领域还是可见光成像领域都是一个极具挑战性的研究方向,对于人脸识别、人脸成像、人脸动画等实际应用更是具有重要意义。针对目前算法复杂度较高、运算量较大且存在局部最优解和初始化不良等问题,本文提出了一种基于深度卷积神经网络的单张图片向3D人脸自动重构算法。该算法首先基于3D转换模型来提取2D人脸图像的密集信息,然后构建深度卷积神经网络架构、设计总体损失函数,直接学习2D人脸图像从像素到3D坐标的映射,从而实现了3D人脸模型的自动构建。算法对比与仿真实验表明,该算法在3D人脸重建上的归一化平均误差更低,且仅需一张2D人脸图像便可自动重构生成3D人脸模型。所生成的3D人脸模型鲁棒性好,重构准确,完整保留表情细节,并且对不同姿态的人脸也具有较好的重建效果,能够在三维空间中无死角自由呈现,将满足更多实际应用需求。     

Eigenspace-based face recognition: a comparative study of different approaches

Eigenspace-based face recognition corresponds to one of the most successful methodologies for the computational recognition of faces in digital images. Starting with the Eigenface-Algorithm, different eigenspace-based approaches for the recognition of faces have been proposed. They differ mostly in the kind of projection method used (standard, differential, or kernel eigenspace), in the projection algorithm employed, in the use of simple or differential images before/after projection, and in the similarity matching criterion or classification method employed. The aim of this paper is to present an independent comparative study among some of the main eigenspace-based approaches. We believe that carrying out independent studies is relevant, since comparisons are normally performed using the implementations of the research groups that have proposed each method, which does not consider completely equal working conditions for the algorithms. Very often, a contest between the abilities of the research groups rather than a comparison between methods is performed. This study considers theoretical aspects as well as simulations performed using the Yale Face Database, a database with few classes and several images per class, and FERET, a database with many classes and few images per class.     

Application of robust face recognition in video surveillance systems

In this paper, we propose a video searching system that utilizes face recognition as searching indexing feature. As the applications of video cameras have great increase in recent years, face recognition makes a perfect fit for searching targeted individuals within the vast amount of video data. However, the performance of such searching depends on the quality of face images recorded in the video signals. Since the surveillance video cameras record videos without fixed postures for the object, face occlusion is very common in everyday video. The proposed system builds a model for occluded faces using fuzzy principal component analysis (FPCA), and reconstructs the human faces with the available information. Experimental results show that the system has very high efficiency in processing the real life videos, and it is very robust to various kinds of face occlusions. Hence it can relieve people reviewers from the front of the monitors and greatly enhances the efficiency as well. The proposed system has been installed and applied in various environments and has already demonstrated its power by helping solving real cases.     

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。     

识别时间可控的人脸识别方案

在已有的人脸识别方法中,识别时间一般随数据库规模而线性增长,因而难以控制,影响算法对大型人脸数据库的实用性。为此,提出了一种新的人脸识别策略:首先通过训练确定一组有代表性人脸作为参考脸,并在此基础上建立基于相似度的排序结构;这样在识别时只需计算待识别人脸与参考脸的相似度,即可结合排序结构确定一组最相似人脸,再逐个比较确定最终识别结果。由于大量计算已离线完成,识别速度大大提高。通过选择参考脸和最相似人脸的数目,可大致控制不同规模数据库的识别时间。实验表明,该识别策略下识别性能略有下降,但识别速度大大提高。     

2D transition metal dichalcogenides for neuromorphic vision system

It has been a long-sought dream for human beings to real-ize a powerful and reliable artificial vision system that can liber-ate human beings from tedious brain work.In the past few years,computer vision based on brain-inspired algorithm has made great achievements in several commercial applications such as the face recognition,medical image diagnosis and driverless vehicles.Nonetheless,the mainstream computer hardware is based on the von Neumann architecture which cannot meet the growing needs for powerful and energy-efficient artificial intelligence.Fortunately,two dimensional(2D) transition metal dichalcogenides (TMDCs) device that can mimic neural architectures may allow us to overcome these challenges.     

使用关键点信息改进弹性匹配人脸识别算法

本文提出了一种增加经典弹性匹配算法对强背景干扰鲁棒性的算法.人脸的自动识别有着广泛的应用前景,弹性匹配是其中的一种重要算法,并有着相对于其他方法更高的鲁棒性,但其并不能有效地防止强背景干扰的影响.本文的主要思路是将局部信息和整体信息相结合,利用没有受到背景干扰影响的局部关键点的位置信息来对基于整体信息的经典弹性匹配方法进行改进.实验结果表明,本文提出的算法有效地提高了弹性匹配识别算法的鲁棒性.     

基于神经网络的人脸自动识别

该文应用神经网络技术构建了一个完整的人脸识别系统。首先使用基于眼睛位置估计的方法从人脸图像中分割出对识别有意义的纯脸,然后使用自组织映射进行特征压缩,提取有效的鉴别特征。最后使用基于知识的模糊神经网络进行分类。在NUSTDBII人脸数据库上的实验得到了令人满意的结果,并且表明该方法对人脸的姿态及表情有一定的不敏感性。     

采用自适应加权扩展LBP的单样本人脸识别

提出了一种采用自适应加权扩展LBP(AWELBP,adaptively weighted extended local binarypattern)的单样本人脸描述方法,首先对单样本的人脸图像进行多尺度分块,对子块的图像进行扩展均匀LBP算子运算,同时同步生成图像局部熵图谱(LEM,local entropy map),计算每一子块对整体人脸图像纹理描述的贡献度图谱,根据贡献度图谱对每个子块的LBP直方图进行自适应加权,最后将各子块的LBP直方图进行连接形成人脸特征。本算法在ORL、Yale、Yale B人脸库上对部分遮挡、表情变化、光照变化等环境进行测试,并与传统算法以及与多种LBP改进算法进行比较,结果表明该算法对部分遮挡、表情变化和光照等环境下单样本人脸描述具有较好的效果。     

The resurgence of push-to-talk technologies

Push-to-talk (PTT) technologies date back to the advent of the telegraph and more recently have been the domain of traditional land mobile radio (LMR) networks. The past few years have brought about a resurgence in PTT as a service offered by commercial providers, driven first by private subscribers and, increasingly, by organizations such as law enforcement agencies that traditionally rely on LMRs. This technology, today one of the growth areas in the communications industry, has received little attention in the scientific literature. In this article, we discuss some of the emerging technologies (voice over IP, CDMA used in 2.5G/3G systems) that relate to today's PTT service. We also discuss the market and financial implications of commercial PTT on current LMR deployments.     

AFRS人脸自动识别系统的设计与开发

人脸检测、跟踪和识别技术是人机自然交互领域中一个富有挑战性的课题,也是近年来研究的一个热点。在新一代(第四代)人机自然交互系统中人脸自动识别系统提供了一个友好的人机交互接口。本文着重介绍了AFRS人脸自动识别系统的设计思想和实现技术。该系统以实现一个实时的、鲁棒的、自动化的系统为目标,融合了人脸检测、跟踪和识别技术以及其它的图像和视频处理技术,并且建立和维护了一个含有人脸特征数据的数据库,从而使得系统可以自动地对进入系统监控范围内的人脸自动进行检测、跟踪和识别。该系统在新一代的人机交互、安保、视频监控等方面有着广泛的应用前景。     

基于智能算法的超材料快速优化设计方法研究进展

目前,超材料研究不断向工程化应用推进,在物理机理与效应、设计理论与方法、加工制备与测试等方面取得了突飞猛进的发展。但是,传统的超材料设计主要依赖人工设计和优化,面对大规模的工程化应用设计时,无法实现数量庞大的超材料结构单元的快速整体设计。近几年,涵盖传统启发式算法和神经网络算法的智能算法在超材料设计中所占的比重逐步上升,基于智能算法设计超材料能够打破传统设计方法在不同基材体系、不同频段以及不同性能指标下设计的局限性,展现出快速设计和架构创新的独特优势。该文综述了包括遗传算法、Hopfield网络算法和深度学习在内的几种典型智能算法在超材料设计中的应用,包括正向设计方法和逆向设计方法。基于智能算法能够实现不同性能指标的频率选择表面、多机理复合吸波超材料、平板聚焦超表面以及异常反射超表面的快速设计,为推动超材料技术的工程化应用提供必要设计手段支撑。      

A self-immune to 3D masks attacks face recognition system

Due to their advantages, facial recognition systems are among the most widely used biometric systems in recent years. However, their drawback is that they can easily be deceived by using 3D masks, which are replicas of real faces. To confirm this fact, we have tested the vulnerability to 3D masks attacks of the already approved Legendre moments invariants (LMI)-based face recognition method. This has been achieved by using the 3D mask attack database (3DMAD), which consists of real faces and faces with 3D masks. The obtained spoof false acceptance rate (SFAR) was close to 65%, which proves that this recognition system is vulnerable to 3D masks attacks. This is generally the case of other face recognition systems, with no anti-spoofing provision. In this paper, a face recognition method is proposed to prevent hackers from deceiving face recognition systems by using 3D masks of people belonging to the system database. This method combines the LMI and the linear discriminant analysis for characteristic features extraction, and the maximum likelihood for classification. With a 97.6% recognition rate and a SFAR equal to 0.83%, the results obtained may be considered as very satisfactory. These results, while obtained with a lower computational time, compare favorably with those of the state-of-the-art method that uses the same 3DMAD database.     

结合CNN不同层信息的全变量建模人脸特征表达学习方法

如何学习有效的人脸特征表达是人脸识别的关键性问题。现有基于卷积神经网络（Convolutional Neural Networks, CNN）的人脸深度特征表达学习方法大多在人脸图像经过了有效检测和校正的情况下，能够获得优异的性能，而在复杂场景下其推广性和鲁棒性受到极大限制。对此，本文提出了结合CNN不同层信息的全变量建模人脸特征表达学习方法，将提取的人脸局部深度特征中所包含的差异信息按照子空间进行建模，有效聚合局部深度特征的同时得到人脸在低维子空间的特征表达（iVector）。在IJB-A（IARPA Janus Benchmark A）上的实验结果表明，与现有的深度特征表达相比，该方法学习得到的人脸iVector表达能够显著提升人脸识别系统的识别性能和计算效率。