基于视频的人脸检测综述

在实时系统中视频人脸的检测与跟踪技术已成为人脸识别领域最活跃的研究方向之一,介绍了人脸检测的应用,对提高检测和跟踪的鲁棒性和精确性问题的理论研究算法进行了总结。分别讨论并评价了人脸检测的几种基本方法,介绍了近年来研究者们研究的新方法并对人脸检测研究中存在的问题和今后的发展进行了讨论。     

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。     

人脸自动定位及其系统实现

人脸自动定位技术在智能视频通信、视频监控以及娱乐等领域有着广泛的应用。通过将基于肤色的人脸检测和基于人工神经网络的控制策略相结合,提出一种新的人脸自动定位算法。该算法简单有效,克服传统跟踪算法中需要利用帧间相关信息和需要标定摄像机的缺点,只需通过人脸检测程序给出人脸特征点在计算机图像中的坐标,就可直接得出摄像机水平调整量和垂直调整量,根据调整量控制摄像机运动即可将人脸自动定位在图像中心。最后利用面向对象的方法实现了系统,并且取得了满意的效果。     

基于Adaboost算法的人脸检测技术的研究与实现

人脸检测是人脸识别技术的基础,首先提出人脸检测系统的构成,分析Adaboost算法对图像进行人脸检测的基本原理。根据Adaboost算法形成了简单的矩形特征作为人脸特征,即Haar-like特征,然后由多个Haar-like特征相当于一个弱分类器,由多个弱分类器级联成为一个强的分类器,并将级联分类器用于动态人脸检测中,从截取的每一帧图像中进行检测。经过实验验证,采用这种方法和步骤进行人脸检测达到了比较好的精度和速度,N-I~T来的人脸识别提供了前提条件。     

基于人脸识别技术应用的安全性研究与实践

随着人工智能技术的快速发展,人脸识别技术在诸多领域得到广泛应用。本文主要针对人脸识别技术的算法缺陷、人脸特征相似、人脸合成等技术本身引发的认证绕过、越权访问等风险进行安全性研究,通过融合基于卷积神经网络的深度学习技术和活体静默检测技术,提升图像声纹识别等性能的同时也大幅提升人脸识别活体检测的性能,杜绝算法缺陷、特征相似和人脸合成攻击而引发的安全风险,为人脸识别技术的发展提供可借鉴的安全防护思路。     

身份认证中灰度共生矩阵和小波分析的活体人脸检测算法

随着身份认证技术的广泛应用,各种假冒合法用户欺骗身份认证系统的手段不断出现。针对这一问题,本文提出了一种基于灰度共生矩阵和小波分析的活体照片人脸检测方法,该方法分析了活体人脸和照片人脸成像后在纹理上的差异性,在人脸灰度共生矩阵的基础上提取能量、熵、惯性矩和相关性四个纹理特征量;同时利用小波变换对人脸图像进行二级分解,提取高频子带系数作为特征向量训练SVM分类识别,算法在公开的数据库NUAA上进行了验证,实验结果表明该方法降低了计算复杂度,提高了检测准确率。      

通过人脸识别技术限制重复投票的电子投票系统的设计

将人脸识别技术应用于电子投票系统中,限制重复投票行为.首先分析了该电子投票系统的结构,给出了人脸识别技术在限制重复投票行为中的应用场景.针对电子投票系统对人脸识别算法的需求以及投票人图像采集背景简单和光照变化较小的特点,分析了适用于本系统的基于AdaBoost的人脸检测方法以及基于特征脸的人脸识别方法,给出了通过OpenCV实现的基于人脸识别方法的身份认证子系统的设计流程,并介绍了基本投票子系统各模块的功能.最后对身份认证子系统的性能进行了分析.     

人脸视频深度伪造与防御技术综述

近年来，得益于深度生成模型的发展，人脸的操控技术取得了巨大突破，以DeepFake为代表的人脸视频深度伪造技术在互联网快速流行，受到了学术界和工业界的广泛重视。这种深度伪造技术通过交换原始人脸和目标人脸的身份信息或编辑目标人脸的属性信息来合成虚假的人脸视频。人脸深度伪造技术激发了很多相关的娱乐应用，如使用面部替换技术将使用者的人脸替换到某段电影片段中，或使用表情重演技术来驱动某个著名人物的静态肖像等。但当前人脸深度伪造技术仍处于快速发展阶段，其生成的真实感和自然度仍有待进一步提升。另一方面，这类人脸深度伪造技术也很容易被不法分子恶意使用，用来制作色情电影、虚假新闻，甚至被用于政要人物来制造政治谣言等，这对国家安全与社会稳定都带来了极大的潜在威胁，因此伪造人脸视频的防御技术至关重要。为了降低深度伪造人脸视频所带来的负面影响，众多学者对伪造人脸视频的检测鉴别技术进行了深入研究，并从不同视角提出了一系列防御方法。然而由于数据集分布形式单一、评价标准不一致、主动性不足等问题，使得防御技术在走向实用的道路上仍有很长一段距离。事实上，人脸深度伪造与防御技术的研究仍旧处在发展期，其技术的内涵与外延正在快速的更新与迭代。本综述将对迄今为止的主要研究工作进行科学系统的总结与归纳，并对现有技术的局限性做简要分析。最后，本文将探讨人脸深度伪造与检测技术的潜在挑战与发展方向，为领域内未来的研究工作提供借鉴。      

生成对抗网络人脸生成及其检测技术研究

随着AIGC的突破性进展,内容生成技术成为社会关注的热点。文章重点分析基于GAN的人脸生成技术及其检测方法。首先介绍GAN的原理和基本架构,然后阐述GAN在人脸生成方面的技术模式。重点对基于GAN在人脸语义生成方面的技术框架进行了综述,包括人脸语义生成发展、人脸语义生成的GAN实现。接着从多视图姿态生成、面部年龄改写、人脸的属性风格生成三个方面展开详细的阐述,并从政策法规、检测技术两个方面对伪造生成人脸图片的检测方法进行了分析。文中将检测技术分成基于深度学习、基于物理、基于生理学、基于人类视觉四个方面,最后对检测技术未来方向进行了展望。     

基于肤色的人脸检测研究

随着科技发展,信息信息技术也在日渐成熟,关于人脸检测技术的研究在不断的更新,检测的方法也多不胜数。像是基于肤色的人脸检测技术就是一种常见的检测技术。今天我就来谈谈基于肤色的人脸检测。     

3T‐FASDM: Linear discriminant analysis‐based three‐tier face anti‐spoofing detection model using support vector machine

In recent years, to solve the problem of face spoofing, momentous work has been done in this field, but still, there is a need for establishing counter measures to the biometric spoofing attacks. Although trained and evaluated on different databases, impressive results have been achieved in existing face anti‐spoofing techniques, but biometric authentication is a very significant problem as imposters are using lots of reconstructed samples or fake synthetic material or structure that can be used for various attack purposes. For the first time, to the best of our knowledge, this paper explains the security for face anti‐spoofing detection using linear discriminant analysis and validates the results by calculating HTER and accuracy on different databases (i.e., REPLAY ATTACK and CASIA). The proposed model, that is, three‐tier face anti‐spoofing detection model (3T‐FASDM), is used for the detection of the fake biometric user and works well for real‐time applications. The proposed methods tested on a set of state‐of‐the‐art anti‐spoofing features for the face mode gives a very low degree of complexity as 26 general image quality measures are applied to differentiate among legitimate and imposter samples. The outcomes obtained from publically available data show that this technique has improved performance and accuracy by analyzing the HTER and machine learning classifiers that are helpful to differentiate among real and fake traits.     

Anti-spoofing enabled face recognition based on aggregated local weighted gradient orientation

Spoofing attack is a catastrophic threat for biometric authentication systems. Inspired by the concept of depth map estimation, a novel anti-spoofing technique based on aggregated local weighted gradient orientation (ALWGO) is proposed. We first estimate the depth of the specimen face image. In the next step, highly discriminant ALWGO features are extracted from the depth map. Finally, a sparse representation classifier is trained to distinguish between the genuine and fake faces. This paper particularly addresses the potential of texture gradient features and their variations, on three types of attacks, viz. printed high-definition photographs, warped photographs and videos displayed on mobile phones. The usage of ALWGO features has been extended for further face recognition. Our proposed approach is robust and nonintrusive as compared to many existing methods. Extensive experimental analysis on publicly available databases clearly demonstrates the superiority of our approach for both face spoofing detection and recognition systems.     

Deep face liveness detection based on nonlinear diffusion using convolution neural network

A face-spoofing attack occurs when an imposter manipulates a face recognition and verification system to gain access as a legitimate user by presenting a 2D printed image or recorded video to the face sensor. This paper presents an efficient and non-intrusive method to counter face-spoofing attacks that uses a single image to detect spoofing attacks. We apply a nonlinear diffusion based on an additive operator splitting scheme. Additionally, we propose a specialized deep convolution neural network that can extract the discriminative and high-level features of the input diffused image to differentiate between a fake face and a real face. Our proposed method is both efficient and convenient compared with the previously implemented state-of-the-art methods described in the literature review. We achieved the highest reported accuracy of 99% on the widely used NUAA dataset. In addition, we tested our method on the Replay Attack dataset which consists of 1200 short videos of both real access and spoofing attacks. An extensive experimental analysis was conducted that demonstrated better results when compared to previous static algorithms results. However, this result can be improved by applying a sparse autoencoder learning algorithm to obtain a more distinguishable diffused image.     

文本检测算法的发展与挑战

对自然场景中的文字进行识别和理解是大量计算机视觉应用的基础。文本检测算法旨在识别出自然图像中的文字信息,目前已经成为计算机视觉和智能信息处理领域研究的一个热点。本文首先对文本检测算法的目标、技术路线及其所面对的挑战进行了分析与介绍。然后回顾了几种经典的文本检测算法,并介绍了两种代表最新研究趋势的深度学习型文本检测算法。进一步,本文阐述了几个主流的文本检测数据集并总结了一些代表性文本检测算法在这些数据集上的检测结果。最后,本文讨论了文本检测的研究现状、面临的挑战和发展的趋势。      

Novel Anti-spoofing Methods Based on Discrete Wavelet Transform in the Acquisition and Tracking Stages of Civil GPS Receiver

The growing dependence of critical civil infrastructure on Global Positioning System (GPS) makes GPS interference not only a safety threat, but also a matter of national security. Spoofing could pose a major threat for GPS navigation systems, so the GPS users have to gain an in-depth understanding of GPS spoofing. Therefore, spoofing countermeasure is a significant subject of research these days. In this paper, we utilize wavelets transform (WT) as a tool that effectively hinders the adverse activities of these groups, and then introduce two novel methods to mitigate spoofing in the acquisition and tracking processes. In the first suggested algorithm, using WT in the acquisition process, we control satellite constellation to mitigate spoofing errors. After generating the in-phase and quadrature correlator output signals, called I and Q respectively, we apply the wavelet db3 to the Q samples to remove their noise components. In the second method, WT is used in a tracking loop. In this way, we apply sym4 to the Q arm, which results in spoofing reduction. We apply our new algorithms to both simulated and measurement data sets, to shed light on its performance. Results show that both methods successfully mitigate the spoofing effect on the tested data sets.     

Throttling spoofed SYN flooding traffic at the source

TCP-based flooding attacks are a common form of Distributed Denial-of-Service (DDoS) attacks which abuse network resources and can bring about serious threats to the Internet. Incorporating IP spoofing makes it even more difficult to defend against such attacks. Among different IP spoofing techniques, which include random spoofing, subnet spoofing and fixed spoofing, subnet spoofing is the most difficult type to fight against. In this paper, we propose a simple and efficient method to detect and defend against TCP SYN flooding attacks under different IP spoofing types, including subnet spoofing. The method makes use of a storage-efficient data structure and a change-point detection method to distinguish complete three-way TCP handshakes from incomplete ones. This lightweight approach makes it relatively easy to deploy the scheme as its resource requirement is reasonably low. Simulation experiments consistently show that our method is both efficient and effective in defending against TCP-based flooding attacks under different IP spoofing types. Specifically, our method outperforms others in achieving a higher detection rate yet with lower storage and computation costs. The research presented in this paper has been supported by a research grant from the Research Grants Council of the Hong Kong Special Administrative Region, China under the Area of Excellence (AoE) Scheme (Project No. AoE/E-01/99).     

Spoofing detection in IEEE 802.15.4 networks based on received signal strength

The shared medium used in wireless networks makes them vulnerable to spoofing attacks, in which an adversary masquerades as one or more legitimate nodes to disturb normal operation of the network. In this paper we present a novel spoofing detection method for static IEEE 802.15.4 networks based on spatial correlation property of received signal strength (RSS). While most existing RSS based techniques directly process RSS values of the received frames and rely on multiple traffic air monitors (AMs) to provide an acceptable detection performance, we extract features of RSS streams to reduce data redundancy and provide a more distinguishable representation of the data. Our algorithm employs two features of RSS streams, summation of detailed coefficients (SDCs) in discrete Haar wavelet transform (DHWT) of the RSS streams and the ratio of out-of-bound frames. We show that in a typical scenario, a single AM with SDC as detection parameter, can theoretically outperform a system with 12 AMs which directly applies RSS values as detection parameter. Using ratio of out-of-bound frames facilitates detection of high rate attacks. In addition, we suggest adaptive learning of legitimate RSS values which enhances the robustness of the attack detector against environmental changes. Using both magnitude and frequency related features, we achieved high detection performance with a single AM; this enables development of preventive measures for spoofing attacks. The performance of our approach was evaluated through an IEEE 802.15.4 testbed in an office environment. Experimental results along with theoretical analysis show that the proposed method outperforms the existing RSS-based spoofing detection solutions. Using a single AM, we were able to attain 94.75% detection rate (DR) with 0.56% false positive rate (FPR). For 4 AMs, the results improved to 99% DR and 0% FPR.     

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.