Abstract

Government agencies are investing a considerable amount of resources into improving security systems as result of recent terrorist events that dangerously exposed flaws and weaknesses in today’s safety mechanisms. Badge or password-based authentication procedures are too easy to hack. Biometrics represents a valid alternative but they suffer of drawbacks as well. Iris scanning, for example, is very reliable but too intrusive; fingerprints are socially accepted, but not applicable to non-consentient people. On the other hand, face recognition represents a good compromise between what’s socially acceptable and what’s reliable, even when operating under controlled conditions. In last decade, many algorithms based on linear/nonlinear methods, neural networks, wavelets, etc. have been proposed. Nevertheless, Face Recognition Vendor Test 2002 shown that most of these approaches encountered problems in outdoor conditions. This lowered their reliability compared to state of the art biometrics. This paper provides an “ex cursus” of recent face recognition research trends in 2D imagery and 3D model based algorithms. To simplify comparisons across different approaches, tables containing different collection of parameters (such as input size, recognition rate, number of addressed problems) are provided. This paper concludes by proposing possible future directions.

Keywords: 2D/3D face recognition; Face databases

Article Outline

1. Face, the most attractive biometric

2. Automatic face recognition: the old and the new

2.1. Linear/nonlinear projection methods

2.2. The neural networks

2.3. Gabor filters and wavelets

2.4. Fractals and Iterated Function Systems (IFSs)

2.5. Thermal and hyperspectral

3. Open questions in face recognition

3.1. The changes in illumination

3.2. The changes in pose

3.3. The occlusion

3.4. The age

3.5. Is there a more general way to state a technique better than others?

4. 3D face recognition

4.1. 3D face data acquisition

4.2. 3D face recognition methods

4.2.1. 2D-based class

4.2.2. 3D-based class

4.2.3. 2D + 3D-based class

5. Discussion and remarks

References