Pedro Tome

Soft Biometrics and Their Application in Person Recognition at a Distance

Soft biometric information extracted from a human body (e.g., height, gender, skin color, hair color, and so on) is ancillary information easily distinguished at a distance but it is not fully distinctive by itself in recognition tasks. However, this soft information can be explicitly fused with biometric recognition systems to improve the overall recognition when confronting high variability conditions. One significant example is visual surveillance, where face images are usually captured in poor quality conditions with high variability and automatic face recognition systems do not work properly. In this scenario, the soft biometric information can provide very valuable information for person recognition. This paper presents an experimental study of the benefits of soft biometric labels as ancillary information based on the description of human physical features to improve challenging person recognition scenarios at a distance. In addition, we analyze the available soft biometric information in scenarios of varying distance between camera and subject. Experimental results based on the Southampton multibiometric tunnel database show that the use of soft biometric traits is able to improve the performance of face recognition based on sparse representation on real and ideal scenarios by adaptive fusion rules.

Identification using face regions: Application and assessment in forensic scenarios

This paper reports an exhaustive analysis of the discriminative power of the different regions of the human face on various forensic scenarios. In practice, when forensic examiners compare two face images, they focus their attention not only on the overall similarity of the two faces. They carry out an exhaustive morphological comparison region by region (e.g., nose, mouth, eyebrows, etc.). In this scenario it is very important to know based on scientific methods to what extent each facial region can help in identifying a person. This knowledge obtained using quantitative and statical methods on given populations can then be used by the examiner to support or tune his observations. In order to generate such scientific knowledge useful for the expert, several methodologies are compared, such as manual and automatic facial landmarks extraction, different facial regions extractors, and various distances between the subject and the acquisition camera. Also, three scenarios of interest for forensics are considered comparing mugshot and Closed-Circuit TeleVision (CCTV) face images using MORPH and SCface databases. One of the findings is that depending of the acquisition distances, the discriminative power of the facial regions change, having in some cases better performance than the full face.

Facial soft biometric features for forensic face recognition.

This paper proposes a functional feature-based approach useful for real forensic caseworks, based on the shape, orientation and size of facial traits, which can be considered as a soft biometric approach. The motivation of this work is to provide a set of facial features, which can be understood by non-experts such as judges and support the work of forensic examiners who, in practice, carry out a thorough manual comparison of face images paying special attention to the similarities and differences in shape and size of various facial traits. This new approach constitutes a tool that automatically converts a set of facial landmarks to a set of features (shape and size) corresponding to facial regions of forensic value. These features are furthermore evaluated in a population to generate statistics to support forensic examiners. The proposed features can also be used as additional information that can improve the performance of traditional face recognition systems. These features follow the forensic methodology and are obtained in a continuous and discrete manner from raw images. A statistical analysis is also carried out to study the stability, discrimination power and correlation of the proposed facial features on two realistic databases: MORPH and ATVS Forensic DB. Finally, the performance of both continuous and discrete features is analyzed using different similarity measures. Experimental results show high discrimination power and good recognition performance, especially for continuous features. A final fusion of the best systems configurations achieves rank 10 match results of 100% for ATVS database and 75% for MORPH database demonstrating the benefits of using this information in practice.

Scenario-based score fusion for face recognition at a distance

The effect of different acquisition distances on the performance of face verification is studied. In particular, we evaluate two standard approaches using popular features (DCT and PCA) and matchers (GMM and SVM) under variation in the acquisition distance, as well as their score-level combination. The DCT-GMM-based system is found to be more robust to acquisition distance degradation than the PCA-SVM-based system. We exploit this fact by introducing an adaptive score fusion scheme based on a novel automatic scenario estimation which is shown to improve our system in uncontrolled environments.

On the vulnerability of iris-based systems to a software attack based on a genetic algorithm

The vulnerabilities of a standard iris verification system to a novel indirect attack based on a binary genetic algorithm are studied. The experiments are carried out on the iris subcorpus of the publicly available BioSecure DB. The attack has shown a remarkable performance, thus proving the lack of robustness of the tested system to this type of threat. Furthermore, the consistency of the bits of the iris code is analysed, and a second working scenario discarding the fragile bits is then tested as a possible countermeasure against the proposed attack.

Acquisition scenario analysis for face recognition at a distance

An experimental analysis of three acquisition scenarios for face recognition at a distance is reported, namely: close, medium, and far distance between camera and query face, the three of them considering templates enrolled in controlled conditions. These three representative scenarios are studied using data from the NIST Multiple Biometric Grand Challenge, as the first step in order to understand the main variability factors that affect face recognition at a distance based on realistic yet workable and widely available data. The scenario analysis is conducted quantitatively in two ways. First, we analyze the information content in segmented faces in the different scenarios. Second, we analyze the performance across scenarios of three matchers, one commercial, and two other standard approaches using popular features (PCA and DCT) and matchers (SVM and GMM). The results show to what extent the acquisition setup impacts on the verification performance of face recognition at a distance.

Analysis of the variability of facial landmarks in a forensic scenario

This paper reports an study of the variability of facial landmarks in a forensic scenario. This variability is affected by two factors: on the one hand, the precision in which the landmarks are tagged (manually or automatically), and on the other hand some other variability factors such as the pose, expression, occlusions, etc. For this study, a mugshot database of 50 persons has been collected following the procedure used by the Spanish Guardia Civil. Mugshots are taken with three distances between the persons and the camera (3, 2, 1 meters) showing the full body, the upper body and the face respectively, obtaining in total 1200 images. 21 facial landmarks are defined and the database was manually tagged imitating the procedure followed by a forensic examiner. This paper analyses the facial landmarking variability for the three distances considered, and also considering the differences obtained for male and female. Results show that landmarks located in the outer part of the face (highest end of the head, ears and chin) present a higher level of variability compared to the landmarks located the inner face (eye region, and nose). Regarding the gender, the landmarks placed in the outer part of the face present a higher level of variability for women compared to men.

A Study of Identification Performance of Facial Regions from CCTV Images

This paper focuses on automatic face identification for forensic applications. Forensic examiners compare different parts of the face image obtained from a closed-circuit television (CCTV) image with a database of mug shots or good quality image(s) taken from the suspect. In this work we study and compare the discriminative capabilities of different facial regions (also referred to as facial features) such as eye, eyebrow, mouth, etc. It is useful because it can statistically support the current practice of forensic facial comparison. It is also of interest to biometrics as a more robust general-purpose face recognition system can be built by fusing the similarity scores obtained from the comparison of different individual parts of the face. For experiments with automatic systems, we simulate a very challenging recognition scenario by using a database of 130 subjects each having only one gallery image. Gallery images are frontal mug shots while probe set consist of low quality CCTV camera images. Face images in gallery and probe sets are first segmented using eye locations and recognition experiments are performed for the different face regions considered. We also study and evaluate an improved recognition approach based on AdaBoost algorithm with Linear Discriminant Analysis (LDA) as a week learner and compare its performance with the baseline Eigenface method for automatic facial feature recognition.

Variability Compensation Using NAP for Unconstrained Face Recognition

The variability presented in unconstrained environments represents one of the open challenges in automated face recognition systems. Several techniques have been proposed in the literature to cope with this problem, most of them tailored to compensate one specific source of variability, e.g., illumination or pose. In this paper we present a general variability compensation scheme based on the Nuisance Attribute Projection (NAP) that can be applied to compensate for any kind of variability factors that affects the face recognition performance. Our technique reduces the intra-class variability by finding a low dimensional variability subspace. This approach is assessed on a database from the NIST still face recognition challenge “The Good, the Bad, and the Ugly” (GBU). The results achieved using our implementation of a state-of-the-art system based on sparse representation are improved significantly by incorporating our variability compensation technique. These results are also compared to the GBU challenge results, highlighting the benefits of adequate variability compensation schemes in these kind of uncontrolled environments.

Fusion of Facial Regions Using Color Information in a Forensic Scenario

This paper reports an analysis of the benefits of using color information on a region-based face recognition system. Three different color spaces are analysed (RGB, YC b C r , lαβ) in a very challenging scenario matching good quality mugshot images against video surveillance images. This scenario is of special interest for forensics, where examiners carry out a comparison of two face images using the global information of the faces, but paying special attention to each individual facial region (eyes, nose, mouth, etc.). This work analyses the discriminative power of 15 facial regions comparing both the grayscale and color information. Results show a significant improvement of performance when fusing several regions of the face compared to just using the whole face image. A further improvement of performance is achieved when color information is considered.