nach oben

2011 | Buch

Handbook of Face Recognition

herausgegeben von: Stan Z. Li, Anil K. Jain

Verlag: Springer London

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This highly anticipated new edition provides a comprehensive account of face recognition research and technology, spanning the full range of topics needed for designing operational face recognition systems. After a thorough introductory chapter, each of the following chapters focus on a specific topic, reviewing background information, up-to-date techniques, and recent results, as well as offering challenges and future directions. Features: fully updated, revised and expanded, covering the entire spectrum of concepts, methods, and algorithms for automated face detection and recognition systems; provides comprehensive coverage of face detection, tracking, alignment, feature extraction, and recognition technologies, and issues in evaluation, systems, security, and applications; contains numerous step-by-step algorithms; describes a broad range of applications; presents contributions from an international selection of experts; integrates numerous supporting graphs, tables, charts, and performance data.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

This chapter provides an introduction to face recognition research. Main steps of face recognition processing are described. Face detection and recognition problems are explained from a face subspace viewpoint. Technology challenges are identified after that. Typical strategies for solving the problems are suggested.

Stan Z. Li, Anil K. Jain

Face Image Modeling and Representation

Frontmatter

Chapter 2. Face Recognition in Subspaces

Abstract

Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision research in general, has witnessed a growing interest in techniques that capitalize on this observation and apply algebraic and statistical tools for extraction and analysis of the underlying manifold. In this chapter, we describe in roughly chronologic order techniques that identify, parameterize, and analyze linear and nonlinear subspaces, from the original Eigenfaces technique to the recently introduced Bayesian method for probabilistic similarity analysis. We also discuss comparative experimental evaluation of some of these techniques as well as practical issues related to the application of subspace methods for varying pose, illumination, and expression.

Gregory Shakhnarovich, Baback Moghaddam

Chapter 3. Face Subspace Learning

Abstract

In this chapter, we will present three groups of dimension reduction algorithms for subspace based face recognition. Specifically, we present the general mean criteria and the max-min distance analysis (MMDA) algorithm; manifold learning algorithms, including the discriminative locality alignment (DLA) and manifold elastic net (MEN); and the transfer subspace learning framework. Experiments on face recognition are also provided.

Wei Bian, Dacheng Tao

Chapter 4. Local Representation of Facial Features

Abstract

Feature extraction is one of the fundamental tasks in computer vision and image processing. Respectively, the task of selecting the best set of features to describe faces for recognition, verification, localization, or detection, is a fundamental problem in face biometrics. In this chapter, we review the most popular and successful features for face biometrics. In general, one should include complete algorithms when comparing the features, but certain extraction methods seem to maintain popularity due to their continuous success in various methods and approaches in biometrics and other fields of computer vision and image processing. This chapter specifically describes in more details two prominent local facial features, the first one based on Gabor filter responses, and the second on more recently proposed local binary patterns (LBPs).

Joni-Kristian Kämäräinen, Abdenour Hadid, Matti Pietikäinen

Chapter 5. Face Alignment Models

Abstract

In order to interpret images of faces (e.g., for recognition), it is important to have a model of the different ways that a face may appear. Though faces vary widely, changes can be broken down into two categories—changes in shape and changes in the texture (patterns of pixel values) across the face—that are largely due to differences between individuals, but also due to changes in expression, viewpoint and lighting conditions. In this chapter, we describe a powerful method of generating compact models of shape and texture variation, and describe two methods—the Active Shape Model (ASM) and Active Appearance Model (AAM)—that fit an appearance model to an unseen image of the face so that we can interpret its underlying properties (e.g., identity).

Phil Tresadern, Tim Cootes, Chris Taylor, Vladimir Petrović

Chapter 6. Morphable Models of Faces

Abstract

In this chapter, we present the Morphable Model, a three-dimensional (3D) representation that enables the accurate modeling of any illumination and pose as well as the separation of these variations from the rest (identity and expression). The Morphable Model is a generative model consisting of a linear 3D shape and appearance model plus an imaging model, which maps the 3D surface onto an image. The 3D shape and appearance are modeled by taking linear combinations of a training set of example faces. We show that linear combinations yield a realistic face only if the set of example faces is in correspondence. A good generative model should accurately distinguish faces from non faces. This is encoded in the probability distribution over the model parameters, which assigns a high probability to faces and a low probability to non faces. The distribution is learned together with the shape and appearance space from the training data.

Reinhard Knothe, Brian Amberg, Sami Romdhani, Volker Blanz, Thomas Vetter

Chapter 7. Illumination Modeling for Face Recognition

Abstract

In this chapter, we show that effective systems can account for the effects of lighting using fewer than 10 degrees of freedom. This can have considerable impact on the speed and accuracy of recognition systems. We will describe theoretical results that, with some simplifying assumptions, prove the validity of low-dimensional, linear approximations to the set of images produced by a face.

Ronen Basri, David Jacobs

Chapter 8. Face Recognition Across Pose and Illumination

Abstract

The last decade has seen automatic face recognition evolve from small-scale research systems to a wide range of commercial products. Driven by the FERET face database and evaluation protocol, the currently best commercial systems achieve verification accuracies comparable to those of fingerprint recognizers. In these experiments, only frontal face images taken under controlled lighting conditions were used. As the use of face recognition systems expands toward less restricted environments, the development of algorithms for view and illumination invariant face recognition becomes important. However, the performance of current algorithms degrades significantly when tested across pose and illumination, as documented in a number of evaluations. In this chapter, we review previously proposed algorithms for pose and illumination invariant face recognition. We then describe in detail two successful appearance-based algorithms for face recognition across pose, eigen light-fields, and Bayesian face subregions. We furthermore show how both of these algorithms can be extended toward face recognition across pose and illumination.

Ralph Gross, Simon Baker, Iain Matthews, Takeo Kanade

Chapter 9. Skin Color in Face Analysis

Abstract

This chapter deals with the role of color in facial image analysis such as face detection and recognition. First, we introduce the use of color information in computer vision in general and in the field of facial image analysis in particular. Then, we give an introduction to color formation and discuss the effect of illumination on color appearance, and its consequences. The skin data can come from different sources like real faces, photos or print. Separating the sources of skin data is presented, and skin color modeling is discussed. We also review the use of color in face detection, while the contribution of color to face recognition is covered.

J. Birgitta Martinkauppi, Abdenour Hadid, Matti Pietikäinen

Chapter 10. Face Aging Modeling

Abstract

One of the challenges in automatic face recognition is to achieve temporal invariance. In other words, the goal is to come up with a representation and matching scheme that is robust to changes due to facial aging. Facial aging is a complex process that affects both the 3D shape of the face and its texture (e.g., wrinkles). These shape and texture changes degrade the performance of automatic face recognition systems. However, facial aging has not received substantial attention compared to other facial variations due to pose, lighting, and expression. We review some of the representative face aging modeling techniques, especially the 3D aging modeling technique. The 3D aging modeling technique adapts view invariant 3D face models to the given 2D face aging database. The evaluation results of the 3D aging modeling technique on three different databases (FG-NET, MORPH and BROWNS) using FaceVACS, a state-of-the-art commercial face recognition engine showed its effectiveness in handling the aging effect.

Unsang Park, Anil K. Jain

Face Recognition Techniques

Frontmatter

Chapter 11. Face Detection

Abstract

Face detection is the first step in automated face recognition. This chapter presents methods and algorithms for building face detectors. Focuses are on AdaBoost learning-based methods because they have been the most successful ones so far in terms of detection accuracy and speed. Effective postprocessing methods are also described. Experimental results are provided.

Stan Z. Li, Jianxin Wu

Chapter 12. Facial Landmark Localization

Abstract

Acquiring facial landmarks, for example, eye contours, mouth corners, nose, etc. is a very important and fundamental work in face recognition and face analysis related areas. This is therefore the task of facial landmark localization. In this chapter, a framework of facial landmark localization is introduced, aimed at finding the accurate positions of the facial feature points. It is a coarse-to-fine approach which could be divided into two main steps: first, precise eye location under probabilistic framework and second, generic facial landmark localization algorithm using random forest embedded active shape model. The algorithms can deal well with images which are unseen in the training set, processing with real time speed.

Xiaoqing Ding, Liting Wang

Chapter 13. Face Tracking and Recognition in Video

Abstract

In this chapter, we describe the utility of videos in enhancing performance of image-based recognition tasks. We discuss a joint tracking-recognition framework that allows for using the motion information in a video to better localize and identify the person in the video using still galleries. We discuss how to jointly capture facial appearance and dynamics to obtain a parametric representation for video-to-video recognition. We discuss recognition in multi-camera networks where the probe and gallery both consist of multi-camera videos. Concluding remarks and directions for future research are provided.

Rama Chellappa, Ming Du, Pavan Turaga, Shaohua Kevin Zhou

Chapter 14. Face Recognition at a Distance

Abstract

Face recognition at a distance is generally motivated by the desire to automatically recognize noncooperative subjects over a wide area. This remote biometric collection and identification problem has been addressed with high-resolution stationary cameras and active camera systems. Key challenges include optical system design, pan-tilt-zoom camera targeting and control, and face recognition with low-resolution images and no pose or illumination control. We discuss major applications, challenges and approaches in this field, and review research literature on this and closely related topics. We further describe a specific face recognition at a distance system that uses the active camera approach, algorithms for facial image modeling and alignment for low-resolution images, and a multi-frame super-resolution process for facial images.

Frederick W. Wheeler, Xiaoming Liu, Peter H. Tu

Chapter 15. Face Recognition Using Near Infrared Images

Abstract

Near infrared (NIR) face recognition has been a successful technology for overcoming illumination changes in face recognition. With years of development, NIR face recognition been in practical use with success and products have appeared in the market. In this chapter, we introduce the NIR face recognition approach, describe the design of active NIR face imaging system, illustrate how to derive from NIR face image an illumination invariant face representation, and provide a learning based method for face feature selection and classification. Experiments are presented.

Stan Z. Li, Dong Yi

Chapter 16. Multispectral Face Imaging and Analysis

Abstract

This chapter addresses the advantages of using multispectral narrow-band images for face recognition, as opposed to conventional broad-band images obtained by color or monochrome cameras. Narrow-band images are by definition taken over a very small range of wavelengths, while broad-band images average the information obtained over a wide range of wavelengths. There are two primary reasons for employing multispectral imaging for face recognition.

Andreas Koschan, Yi Yao, Hong Chang, Mongi Abidi

Chapter 17. Face Recognition Using 3D Images

Abstract

In this chapter, we present advances that aid in overcoming the challenges encountered in 3D face recognition. First, we present a fully automatic 3D face recognition system, UR3D, which has been proven to be robust under variations in expressions. Second, we demonstrate how to handle pose variations. Finally, we demonstrate how the problems related to the cost and unfriendliness of 3D scanners can be mitigated through hybrid systems.

I. A. Kakadiaris, G. Passalis, G. Toderici, E. Efraty, P. Perakis, D. Chu, S. Shah, T. Theoharis

Chapter 18. Facial Action Tracking

Abstract

This chapter explains the basics of parametric face models used for face and facial action tracking as well as fundamental strategies and methodologies for tracking. A few tracking algorithms serving as pedagogical examples are described in more detail.

Jörgen Ahlberg, Igor S. Pandzic

Chapter 19. Facial Expression Recognition

Abstract

This chapter introduces recent advances in facial expression analysis and recognition. The first part discusses general structure of AFEA systems. The second part describes the problem space for facial expression analysis. This space includes multiple dimensions: level of description, individual differences in subjects, transitions among expressions, intensity of facial expression, deliberate versus spontaneous expression, head orientation and scene complexity, image acquisition and resolution, reliability of ground truth, databases, and the relation to other facial behaviors or nonfacial behaviors. We note that most work to date has been confined to a relatively restricted region of this space. The last part of this chapter is devoted to a description of more specific approaches and the techniques used in recent advances. They include the techniques for face acquisition, facial data extraction and representation, facial expression recognition, and multimodal expression analysis. The chapter concludes with a discussion assessing the current status, future possibilities, and open questions about automatic facial expression analysis.

Yingli Tian, Takeo Kanade, Jeffrey F. Cohn

Chapter 20. Face Synthesis

Abstract

How to synthesize photorealistic images of human faces has been a fascinating yet difficult problem in computer graphics. Here, the term “face synthesis” refers to synthesis of still images as well as synthesis of facial animations. In this chapter, we focus more on the synthesis of still images and skip most of the aspects that mainly involve the motion over time. We review recent advances on face synthesis including 3D face modeling, face relighting, and facial expression synthesis.

Yang Wang, Zicheng Liu, Baining Guo

Performance Evaluation: Machines and Humans

Chapter 21. Evaluation Methods in Face Recognition

Abstract

The heart of designing and conducting evaluations and is the experimental protocol. The protocol states how an evaluation is to be conducted and how the results are to be computed. In this chapter we concentrate on describing the FERET and FRVT 2002 protocols. The FRVT 2002 evaluation protocol is based in the FERET evaluation protocols. The FRVT 2002 protocol is designed for biometric evaluations in general, not just for evaluating face recognition algorithms. These two evaluation protocol served as a basis for the FRVT 2006 and MBE 2010 evaluations.

P. Jonathon Phillips, Patrick Grother, Ross Micheals

Chapter 22. Dynamic Aspects of Face Processing in Humans

Abstract

In this chapter, we will focus on the role of motion in identity and expression recognition in human, and its developmental and neurophysiological aspects. Based on results from literature, we make it clear that there is some form of characteristic facial information that is only available over time, and that it plays an important role in the recognition of identity, expression, speech, and gender; and that the addition of dynamic information improves the recognizability of expressions and identity, and can compensate for the loss of static information. Moreover, at least several different types of motion seem to exist, they play different roles, and a simple rigid/nonrigid dichotomy is neither sufficient nor appropriate to describe these motions. Additional research is necessary to determine what the dynamic features for face processing are.

Heinrich H. Bülthoff, Douglas W. Cunningham, Christian Wallraven

Chapter 23. Face Recognition by Humans and Machines

Abstract

By the standards of automated face recognition systems, human performance is notable in its ability to operate robustly across changes in illumination, pose, and expression. This chapter presents a comparative examination of face recognition by humans and machines. The first part contains an overview of the basic characteristics of human face representations, with emphasis both on the strengths and weaknesses of this code. The second part of the chapter, considers recent comparisons between humans and automated face recognition algorithms. These include benchmarking the performance of algorithms against humans, the fusion of human and machine judgments of identity, and the robustness of algorithms operating in ethnically diverse environments. The evaluation of machine performance in the context of human skills can give insight into the challenges of face recognition in uncontrolled environments and into the strategies humans have evolved to overcome these challenges.

Alice J. O’Toole

Face Recognition Applications

Frontmatter

Chapter 24. Face Recognition Applications

Abstract

As one of the most nonintrusive biometrics, face recognition technology is becoming ever closer to people’s daily lives. Evidence of this is that in 2000 the International Civil Aviation Organization endorsed facial recognition as the most suitable biometrics for air travel. To our knowledge, no review papers are available on the newly enlarged application scenarios since then. We hope this chapter will be an extension of the previous studies. We review many face recognition applications that have already used face recognition technologies. This set of applications is a much larger super-set of previously reviewed. We also review some other new scenarios that will potentially utilize face recognition technologies in the near future.

Thomas Huang, Ziyou Xiong, Zhenqiu Zhang

Chapter 25. Large Scale Database Search

Abstract

This chapter focuses on large scale search systems for the biometric and face recognition, in particular, on issues related to scalability, system throughput, biometric accuracy, and database sanitization.

Michael Brauckmann, Christoph Busch

Chapter 26. Face Recognition in Forensic Science

Abstract

In this chapter, we will first explain the current means of comparing faces used by forensic science laboratories. It is a nonautomated process performed by forensic examiners and has been referred to as facial “photographic comparison” or forensic facial identification. Next, we will outline the innovative ways in which facial recognition systems are being used by the forensic community. Lastly, we will discuss the growing future of facial biometrics in the legal system and the increasing (not decreasing) need for human examiners to perform facial identification in combination with the automated facial recognition systems.

Nicole A. Spaun

Chapter 27. Privacy Protection and Face Recognition

Abstract

In this chapter, we describe the privacy issues surrounding the proliferation of digital imagery, particularly of faces, in surveillance video, online photo-sharing, medical records and online navigable street imagery. We highlight the growing capacity for computer systems to process, recognize, and index face images and outline some of the techniques that have been used to protect privacy while supporting ongoing innovation and growth in the applications of digital imagery.

Andrew W. Senior, Sharathchandra Pankanti

Backmatter

Titel: Handbook of Face Recognition
herausgegeben von: Stan Z. Li
Anil K. Jain
Verlag: Springer London
Electronic ISBN: 978-0-85729-932-1
Print ISBN: 978-0-85729-931-4
DOI: https://doi.org/10.1007/978-0-85729-932-1