Andrea Lagorio

On the Use of SIFT Features for Face Authentication

Several pattern recognition and classification techniques have been applied to the biometrics domain. Among them, an interesting technique is the Scale Invariant Feature Transform (SIFT), originally devised for object recognition. Even if SIFT features have emerged as a very powerful image descriptors, their employment in face analysis context has never been systematically investigated. This paper investigates the application of the SIFT approach in the context of face authentication. In order to determine the real potential and applicability of the method, different matching schemes are proposed and tested using the BANCA database and protocol, showing promising results.

Distinctiveness of faces: A computational approach

This paper develops and demonstrates an original approach to face-image analysis based on identifying distinctive areas of each individuals face by its comparison to others in the population. The method differs from most others—that we refer as unary—where salient regions are defined by analyzing only images of the same individual. We extract a set of multiscale patches from each face image before projecting them into a common feature space. The degree of “distinctiveness” of any patch depends on its distance in feature space from patches mapped from other individuals. First a pairwise analysis is developed and then a simple generalization to the multiple-face case is proposed. A perceptual experiment, involving 45 observers, indicates the method to be fairly compatible with how humans mark faces as distinct. A quantitative example of face authentication is also performed in order to show the essential role played by the distinctive information. A comparative analysis shows that performance of our n-ary approach is as good as several contemporary unary, or binary, methods, while tapping a complementary source of information. Furthermore, we show it can also provide a useful degree of illumination invariance.

Facial Template Synthesis based on SIFT Features

This paper proposes a procedure for facial template synthesis based on features extracted from multiple facial instances with varying pose. The proposed system extracts the rotation, scale and translation invariant SIFT features, also having high discrimination ability, from the frontal and half left and right profiles of an individual face images. These affine invariant features obviate the need of ad-hoc algorithms to register features of side profiles against frontal profiles for feature-set augmentation. An augmented feature set is then formed from the fusion of features from frontal and side profiles of an individual, after removing feature redundancy. The augmented feature sets of database and query images are matched using the Euclidean distance and Point pattern matching techniques. The experimental results are compared with the system using only frontal face images for both the matching strategies. The reported results prove the efficacy of the proposed system.

Automatic Detection of Adverse Weather Conditions in Traffic Scenes

Visual surveillance in outdoor environments requires the monitoring of both objects and events. The analysis is generally driven by the target application which, in turn, determines the set of relevant events and objects to be analyzed. In this paper we concentrate on the analysis of outdoor scenes, in particular for vehicle traffic control. In this scenario, the analysis of weather conditions is considered to signal particular and potentially dangerous situations like the presence of snow, fog, or heavy rain. The developed system uses a statistical framework based on the mixture of Gaussians to identify changes both in the spatial and temporal frequencies which characterize specific meteorological events. Several experiments performed on standard databases and real scenes demonstrate the applicability of the proposed approach.

Understanding critical factors in appearance-based gender categorization

Gender categorization, based on the analysis of facial appearance, can be useful in a large set of applications. In this paper we investigate the gender classification problem from a non-conventional perspective. In particular, the analysis will aim to determine the factors critically affecting the accuracy of available technologies, better explaining differences between face-based identification and gender categorization. A novel challenging protocol is proposed, exploiting the dimensions of the Face Recognition Grand Challenge version 2.0 database (FRGC2.0). This protocol is evaluated against several classification algorithms and different kind of features, such as Gabor and LBP. The results obtained show that gender classification can be made independent from other appearance-based factors such as the skin color, facial expression, and illumination condition.

Automated quality control of printed flasks and bottles

The paper faces the quality control problem for printed flasks, bottles and cans, used as containers for drugs and beverages. The control is mainly aimed at identifying ink spots and faded prints produced by a serigraphic process, but the approach is generically applicable to any kind of printing and printed cylindrical surface. Differently from the existing systems, based on the acquisition of good printed samples, the automatic control is based on the original digital image feeded to the printing system. Therefore, the control takes place directly between the ideal model and the result of a complex printing process including a number of distortion and noise sources. Problems related to image acquisition, reconstruction and alignment are investigated; a novel technique for image-model verification, based on adaptive local deformation, is also proposed and tested over a significant set of samples. A complete prototype system designed for such quality control is finally described and its operating capability on the field is discussed.

Design of a vision system for identity verification

The use of biometric data for automated identity verification, is one of the major challenges in many application domains. This is certainly a formidable task which requires the development of a complex system including several concurrent agents operating in real time. In this paper a system for automated identity verification (currently under development within an European research project) encompassing the active vision paradigm is described. In our approach the amount of data to be processed is limited by selecting and analysing only few areas within the face image. The number of pixels for each area are also reduced by applying a space-variant conformal mapping. The devised system does not require to use special hardware. On the other hand, robustness can be enforced by performing the final matching with more than a single image. This may require to adopt a simple, coarse scale, multi-processor architecture. The system is conceived for banking applications but can be ported to a variety of industrial applications. Several experiments on identity verification, performed on real images, are presented.

Iconic Methods for Multimodal Face Recognition: A Comparative Study

When dealing with face recognition, multimodal algorithms, with their potential to capture complementary characteristics from the 2D and 3D data channels, can reach high level of efficiency and robustness. In this paper, we explore different combinations of iconic descriptors coupled with a shape descriptor and propose a fully automatic, multimodal, face recognition paradigm. Two iconic features extractors, the Scale Invariant Feature Transform (SIFT) and the Speeded-Up Robust Features (SURF), are used, in turn, to extract salient points from the images of the faces. The corresponding points on the scans are validated with Joint Differential Invariants, a 3D characterisation method based on local and global shape information. SIFT and SURF are then combined at feature level and the 3D Joint Differential Invariants used to validate them on the shape channel. The proposed method has been tested on the FRGCv2 database. Experimental results highlight the complementarity of the feature points extracted by SIFT and SURF and the effectiveness of their 3D validation.

Blending 2D and 3D Face Recognition

Over the last decade, performance of face recognition algorithms systematically improved. This is particularly impressive when considering very large or challenging datasets such as the FRGC v2 or Labelled Faces in the Wild . A better analysis of the structure of the facial texture and shape is one of the main reasons of improvement in recognition performance. Hybrid face recognition methods , combining holistic and feature-based approaches, also allowed to increase efficiency and robustness. Both photometric information and shape information allow to extract facial features which can be exploited for recognition. However, both sources, grey levels of image pixels and 3D data , are affected by several noise sources which may impair the recognition performance. One of the main difficulties in matching 3D faces is the detection and localization of distinctive and stable points in 3D scans. Moreover, the large amount of data (tens of thousands of points) to be processed make the direct one-to-one matching a very time-consuming process. On the other hand, matching algorithms based on the analysis of 2D data alone are very sensitive to variations in illumination, expression and pose. Algorithms, based on the face shape information alone, are instead relatively insensitive to these sources of noise. These mutually exclusive features of 2D- and 3D-based face recognition algorithm call for a cooperative scheme which may take advantage of the strengths of both, while coping for their weaknesses. We envisage many real and practical applications where 2D data can be used to improve 3D matching and vice versa. Towards this end, this chapter highlights both the advantages and disadvantages of 2D- and 3D-based face recognition algorithms . It also explores the advantages of blending 2D- and 3D data -based techniques, also proposing a novel approach for a fast and robust matching. Several experimental results, obtained from publicly available datasets, currently at the state of the art, demonstrate the effectiveness of the proposed approach.

Face recognition by local and global analysis

Faces are highly deformable objects which may easily change their appearance over time. Not all face areas are subject to the same variability and they do not have the same relevance for recognition. Therefore, selecting and decoupling the information from independent areas of the face is of paramount importance to improve the robustness of any face recognition technique. In forensic applications it is rather important to identify an individual by peculiar, subjective features, which uniquely characterize his/her face. This paper discusses how to select relevant local features on the face and use these features to uniquely identify a subject. For identification purposes, both a global and local (as recognition from parts) matching strategy is proposed. The local strategy is based on matching individual salient facial SIFT features as connected to selected facial landmarks. As for the global matching strategy, relevant SIFT features are combined together to form a single feature.