现在位置: >

Face recognition A summary of 1995–

The development of face recognition over the past years allows an organization into three types of recognition algorithms, namely frontal, profile, and view-tolerant recognition, depending on the kind of imagery and the according recognition algorithms. Wh

Face Recognition: a Summary of 1995 - 1997

Thomas Fromherz

International Computer Science Institute

1947 Center St, Suite 600

Berkeley, CA 94704

Phone: +1 510 642 4274 ext. 115

Email: fromherz@icsi.berkeley.edu

Keywords: Face recognition, identification, authentication, hybrid recognition, classifiers

Abstract

The development of face recognition over the past years allows an organization into three types of recognition algorithms, namely frontal, profile, and view-tolerant recognition, depending on the kind of imagery and the according recognition algorithms. While frontal recognition certainly is the classical approach, view-tolerant algorithms usually perform recognition in a more sophisticated fashion by taking into consideration some of the underlying physics, geometry, and statistics. Profile schemes as stand-alone systems have a rather marginal significance for identification. However, they are very practical either for fast coarse pre-searches of large face databases to reduce the computational load for a subsequent sophisticated algorithm, or as part of a hybrid recognition scheme.

Such hybrid approaches have a special status among face recognition systems as they combine different recognition approaches in an either serial or parallel order to overcome the shortcomings of the individual components.

1Introduction

The following report is a summary of a longer and more comprehensive survey written in 1997 [Fromherz et al. 97], reporting on research results mostly published in the years 1995 until mid 1997, thus complementing the earlier surveys by [Samal & Igenar 92] on nonconnectionist approaches, by [Valentin et al. 94] on connectionist schemes, and the abundant survey by [Chellappa et al. 95] on 20 years of face recognition.

Modern face recognition has reached an identification rate of greater than 90% for larger databases with well-controlled pose and illumination conditions. While this is a high rate for face recognition, it is by no means comparable to using keys or batches, and not at all to a human concierge. Still, face recognition as an identification or authentication means could be successfully employed in many such tasks like entrance control, computer access control, or in the prominent field of criminal investigation. Latest news about commercial systems such as Visionics "FaceIt" even promise to bring face recognition to an extensive use in the American Department of Motor Vehicles or at ATM machines.

The development of face recognition over the past years allows an organization into three types of recognition algorithms, namely frontal, profile, and view-tolerant recognition, depending on both the kind of imagery (facial views) available, and on the according recognition algorithms. While frontal recognition certainly is the classical approach to tackle the problem at hand, view-tolerant algorithms usually treat it in a more sophisticated fashion by taking into consideration some of the underlying physics, geometry, and statistics.

In addition to this organization, a special status is taken by the rather novel idea of hybrid recognition algorithms, which combine different recognition approaches in either a serial or parallel order. In the parallel case submitting all single recognition rates to one of a number of possible classification procedures assesses the final results.

The following chapter gives an overview of existing frontal, profile and view-tolerant recognition approaches. The special class of hybrid recognition systems is treated in chapter 3. Some conclusions are given in chapter 4.

2Modern Face Recognition

In this survey report, a rather "high-level" overview of face recognition is proposed by a classification into frontal, profile, and view-tolerant face recognition. It is interesting to note that the majority of direct contributions on face recognition in the two major conferences on face and gesture recognition covered in this report, 1995 in Zurich, and 1996 in Killington, chose a modern view-tolerant rather than a classical frontal approach.

相关文档
相关主题
返回顶部
热门文档