Work Experience

  • Present 2008

    Computer Vision Researcher

    IT - Instituto de Telecomunicações,
    Covilhã

  • 2012 2012

    Independent Consultant

    TFV - Sistemas Informáticos, S.A.,
    Lisbon

  • 2009 2011

    Class Monitor

    University of Beira Interior, Covilhã

Education

  • Ph.D. 2015

    Ph.D. in Computer Science

    University of Beira Interior

  • M.Sc.2009

    M.Sc. in Computation and Intelligent Systems

    University of Beira INterior

  • B.Sc.2007

    B.Sc. in Computer Science and Engineering

    University of Beira Interior

Research Projects

  • image

    Quis-Campi

    Biometric Recognition in Surveillance Environments

    A fully automated biometric recognition system, able to work in completely covert conditions.

    The acronym of this proposal comes from the Latin and summarizes its goals: "Quis" stands for "Who is" and "Campus" refers to a delimited space. Hence, in this project we aim at research and development of a biometric recognition system able to work in completely covert conditions. The main idea is that whenever a subject enters a QUIS-CAMPUS, it is automatically recognized, using multiple biometric sources and without requiring any active participation from the subject side.

  • image

    Necovid

    Covert Negative Biometric Recognition

    The main purpose of this project is to address the feasibility of an automated system that performs covert and reliable biometric recognition, using the iris as single trait. Obviously, this type of biometric recognition is extremely ambitious and brings many challenges to the pattern recognition task, namely due to the many types of non-deal images that result of the imaging conditions and acquisition protocols (at-a-distance, on-the-move and under dynamic lighting conditions) The proposed approach to deal with these extremely challenging conditions is based on the concept of negative (a-contrario) recognition, i.e., to prove that an individual is not among a group of people already known to the system. The key insight is that although the quality of the captured data possibly denies the positive recognition with enough confidence, perhaps it is still possible to assure that data is not correspondent to a subset of the enrolled templates, which for most of the everyday situations is the essential. The range of potential applications to the type of system proposed for this project is obvious. Indeed, this type of applications is regarded for the Pattern Recognition community as "the grand-challenge" (e.g., "Biometrics: a grand-challenge", A.K. Jain), due to the implications that they can have in modern societies.

    Project Site

  • image

    BioRec

    Non-Cooperative Multimodal Biometric Recognition

    The goal of the project is the development of a system for recognizing people at a distance without their cooperation, using iris and face (on the visible and infrared) detection and recognition techniques. The project has developed new methods for: iris segmentation in the visible wavelength; iris recognition in the visible wavelength; real-time face detection in the visible wavelength; face segmentation in the visible and far infrared; face recognition in visible wavelength; motion tracking in the far infrared; gender recognition from visible wavelength face images.

    Project Site

Filter by type:

Sort by year:

BioHDD: A Dataset for Studying Biometric Identification on Heavily Degraded Data

Gil Santos, Paulo T. Fiadeiro, Hugo Proença
Journal Paper IET Biometrics, ISSN: 2047-4938, DOI: 10.1049/iet-bmt.2014.0045

Abstract

Substantial efforts have been put into bridging the gap between biometrics and visual surveillance, in order to develop automata able to recognise human beings 'in the wild'. This study focuses on biometric recognition in extremely degraded data, and its main contributions are three-fold: (1) announce the availability of an annotated dataset that contains high quality mugshots of 101 subjects, and large sets of probes degraded extremely by 10 different noise factors; (2) report the results of a mimicked watchlist identification scheme: an online survey was conducted, where participants were asked to perform positive and negative identification of probes against the enrolled identities. Along with their answers, volunteers had to provide the major reasons that sustained their responses, which enabled the authors to perceive the kind of features that are most frequently associated with successful/failed human identification processes. As main conclusions, the authors observed that humans rely greatly on shape information and holistic features. Otherwise, colour and texture-based features are almost disregarded by humans; (3) finally, the authors give evidence that the positive human identification on such extremely degraded data might be unreliable, whereas negative identification might constitute an interesting alternative for such cases.

Fusing Iris and Periocular Information for Cross-Sensor Recognition

Gil Santos, Emanuel Grancho, Marco V. Bernardo, Paulo T. Fiadeiro
Journal Paper Elsevier Pattern Recognition Leters, DOI: 10.1016/j.patrec.2014.09.012

Abstract

In recent years, the usage of mobile devices has increased substantially, as have their capabilities and applications. Extending biometric technologies to these gadgets is desirable because it would facilitate biometric recognition almost anytime, anywhere, and by anyone. The present study focuses on biometric recognition in mobile environments using iris and periocular information as the main traits. Our study makes three main contributions, as follows. (1) We demonstrate the utility of an iris and periocular dataset, which contains images acquired with 10 different mobile setups and the corresponding iris segmentation data. This dataset allows us to evaluate iris segmentation and recognition methods, as well as periocular recognition techniques. (2) We report the outcomes of device-specific calibration techniques that compensate for the different color perceptions inherent in each setup. (3) We propose the application of well-known iris and periocular recognition strategies based on classical encoding and matching techniques, as well as demonstrating how they can be combined to overcome the issues associated with mobile environments.

Using Ocular Data for Unconstrained Biometric Recognition

Hugo Proença, Gil Santos, João C. Neves
Book Chapter Face Recognition in Adverse Conditions, Maria De Marsico, Michele Nappi, Massimo Tistarelli (Eds.), Advances in Computational Intelligence and Robotics Book Series, IGI Global, 2014, ISSN: 2327-0411
image

Abstract

There are several scenarios where a full facial picture cannot be obtained nor the iris properly imaged. For such cases, a good possibility might be to use the ocular region for recognition, which is a relatively new idea and is regarded as a good trade-off between using the whole face or the iris alone. The area in the vicinity of the eyes is designated as periocular and is particularly useful on less constrained conditions, when image acquisition is unreliable, or to avoid iris pattern spoofing. This chapter provides a comprehensive summary of the most relevant research conducted in the scope of ocular (periocular) recognition methods. The authors compare the main features of the publicly available data sets and summarize the techniques most frequently used in the recognition algorithms in this chapter. In addition, they present the state-of-the-art results in terms of recognition accuracy and discuss the current issues on this topic, together with some directions for further work.

Segmenting the Periocular Region using a Hierarchical Graphical Model Fed by Texture / Shape Information and Geometrical Constraints

Hugo Proença, João C. Neves, Gil Santos
Conference Papers Proceedings of the International Joint Conference on Biometrics - IJCB 2014, Clearwater, Florida, U.S.A., September 29 - October 2

Abstract

Using the periocular region for biometric recognition is an interesting possibility: this area of the human body is highly discriminative among subjects and relatively stable in appearance. In this paper, the main idea is that improved solutions for defining the periocular region-of-interest and better pose / gaze estimates can be obtained by segmenting (labelling) all the components in the periocular vicinity. Accordingly, we describe an integrated algorithm for labelling the periocular region, that uses a unique model to discriminate between seven components in a single-shot: iris, sclera, eyelashes, eyebrows, hair, skin and glasses. Our solution fuses texture / shape descriptors and geometrical constraints to feed a two-layered graphical model (Markov Random Field), which energy minimization provides a robust solution against uncontrolled lighting conditions and variations in subjects pose and gaze.

Periocular Biometrics: An Emerging technology for Unconstrained Scenarios

Gil Santos, Hugo Proença
Conference Papers Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management - CIBIM 2013, Singapore, April 16-19, pag. 14-21, ISBN: 978-1-4673-5879-8/13

Abstract

The periocular region has recently emerged as a promising trait for unconstrained biometric recognition, specially on cases where neither the iris and a full facial picture can be obtained. Previous studies concluded that the regions in the vicinity of the human eye - the periocular region - have surprisingly high discriminating ability between individuals, are relatively permanent and easily acquired at large distances. Hence, growing attention has been paid to periocular recognition methods, on the performance levels they are able to achieve, and on the correlation of the responses given by other. This work overviews the most relevant research works in the scope of periocular recognition: summarizes the developed methods, and enumerates the current issues, providing a comparative overview. For contextualization, a brief overview of the biometric field is also given.

Facial Expressions: Discriminability of Facial Regions and Relationship to Biometrics Recognition

Elisa Barroso, Gil Santos, Hugo Proença
Conference Papers Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management - CIBIM 2013, Singapore, April 16-19, pag. 77-80, ISBN: 978-1-4673-5879-8/13

Abstract

Facial expressions result from movements of muscular action units, in response to internal emotion states or perceptions, and it has been shown that they decrease the performance of face-based biometric recognition techniques. This paper focuses in the recognition of facial expressions and has the following purposes: 1) confirm the suitability of using dense image descriptors widely known in biometrics research (e.g., local binary patterns and histograms of oriented gradients) to recognize facial expressions; 2) compare the effectiveness attained when using different regions of the face to recognize expressions; 3) compare the effectiveness attained when the identity of subjects is known / unknown, before attempting to recognize their facial expressions.

A Fusion Approach to Unconstrained Iris Recognition

Gil Santos, Edmundo Hoyle
Journal Paper Elsevier Pattern Recognition Leters, vol. 33, num. 8, pag. 984-990, June 2012, DOI: 10.1016/j.patrec.2011.08.17

Abstract

As biometrics has evolved, the iris has remained a preferred trait because its uniqueness, lifetime stability and regular shape contribute to good segmentation and recognition performance. However, commercially deployed systems are characterized by strong acquisition constraints based on active subject cooperation, which is not always achievable or even reasonable for extensive deployment in everyday scenarios. Research on new techniques has been focused on lowering these constraints without significantly impacting performance while increasing system usability, and new approaches have rapidly emerged. Here we propose a novel fusion of different recognition approaches and describe how it can contribute to more reliable non-cooperative iris recognition by compensating for degraded images captured in less constrained acquisition setups and protocols under visible wavelengths and varying lighting conditions. The proposed method was tested at the NICE.II (Noisy Iris Challenge Evaluation - Part 2) con- test, and its performance was corroborated by a third-place finish.

Fusing Color and Shape Descriptors in the Recognition of Degraded Iris Images Acquired at Visible Wavelength

Hugo Proença, Gil Santos
Journal Paper Elsevier Computer Vision and Image Understanding, , volume 116, pag. 167-178, ISSN: 1077-3142, DOI: 10.1016/j.cviu.2011.10.008

Abstract

Despite the substantial research into the development of covert iris recognition technologies, no machine to date has been able to reliably perform recognition of human beings in real-world data. This limitation is especially evident in the application of such technology to large-scale identification scenarios, which demand extremely low error rates to avoid frequent false alarms. Most previously published works have used intensity data and performed multi-scale analysis to achieve recognition, obtaining encouraging performance values that are nevertheless far from desirable. This paper presents two key innovations. (1) A recognition scheme is proposed based on techniques that are substantially different from those traditionally used, starting with the dynamic partition of the noise-free iris into disjoint regions from which MPEG-7 color and shape descriptors are extracted. (2) The minimal levels of linear correlation between the outputs produced by the proposed strategy and other state-of-the-art techniques suggest that the fusion of both recognition techniques significantly improve performance, which is regarded as a positive step towards the development of extremely ambitious types of biometric recognition.

A Robust Eye-Corner Detection Method for Real-World Data

Gil Santos, Hugo Proença
Conference Papers Proceedings of the IEEE International Joint Conference on Biometrics - IJCB 2011, Washington DC, U.S.A., October 11-13

Abstract

Corner detection has been motivating several research works and is particularly important in different computer vision tasks, acting as basis for further image understanding stages. Particularly, the detection of eye-corners in facial images is relevant for domains such as biometric systems and assisted-driving systems. Having empirically evaluated the state-of-the-art of eye-corner detection proposals, we observed that they only achieve satisfactory results when dealing with good quality data. Hence, in this paper we describe an eyecorner detection method with particular focus on robustness, i.e., the suitability to deal with degraded data, toward the applicability in real-world conditions. Our experiments show that the proposed method outperforms others either in noise-free and degraded data (blurred, rotated and with significant variations in scale), which is regarded as the main achievement.

Iris Recognition: Preliminary Assessment about the Discriminating Capacity of Visible Wavelength Data

Gil Santos, Marco V. Bernardo, Paulo T. Fiadeiro, Hugo Proença
Conference Papers Sixth IEEE International Workshop on Multimedia Information Processing and Retrieval (MIPR 2010) Taichung, Taiwan, December 13 - December 15, pag. 324-329, ISBN: 978-0-7695-4217-1

Abstract

The human iris supports contactless data acquisition and can be imaged covertly. These factors give raise to the possibility of performing biometric recognition procedure without subjects’ knowledge and in uncontrolled data acquisition scenarios. The feasibility of this type of recognition has been receiving increasing attention, as is of particular interest in visual surveillance, computer forensics, threat assessment, and other security areas. In this paper we stress the role played by the spectrum of the visible light used in the acquisition process and assess the discriminating iris patterns that are likely to be acquired according to three factors: type of illuminant, it's luminance, and levels of iris pigmentation. Our goal is to perceive and quantify the conditions that appear to enable the biometric recognition process with enough confidence.

Iris Recognition: Analysing the Distribution of the Iriscodes Concordant Bits

Gil Santos, Hugo Proença
Conference Papers IEEE Proceedings of the 3rd International Congress on Image and Signal Processing (CISP 2010), Yantai, China, October 16 - October 18, vol. 4, pag. 1873-1877

Abstract

The growth in practical applications for iris biometrics has been accompanied by relevant developments in the underlying algorithms and techniques. Efforts are being made to minimize the tradeoff between the recognition error rates and data quality, acquired in the visible wavelength, in less controlled environments, over simplified acquisition protocols and varying lighting conditions. This paper presents an approach that can be regarded as an extension to the widely known Daugman's method. Its basis is the analysis of the distribution of the concordant bits when matching iriscodes on both the spatial and frequency domains. Our experiments show that this method is able to improve the recognition performance over images captured in less constrained acquisition setups and protocols. Such conclusion was drawn upon trials conducted for multiple datasets.

On the Role of Interpolation in the Normalization of Non-Ideal Visible Wavelength Iris Images

Gil Santos, Hugo Proença
Conference Papers IEEE Proceedings of the 2009 International Conference on Computational Intelligence and Security (CIS'09), Beijing, China, December 11 - December 14, vol 1, pag. 315-319, ISBN: 978-0-7695-3931-7

Abstract

The growth in practical applications for iris biometrics has been accompanied by relevant developments in the underlying algorithms and techniques. Along with the research focused on near-infrared (NIR) cooperatively captured images, efforts are being made to minimize the trade-off between the quality of the captured data and the recognition accuracy on less constrained environments, where images are obtained at the visible wavelength, at increased distances, over simplified protocols and adverse lightning. This paper addresses the effect of the interpolation method, used in the iris normalization stage, in the overall recognition error rates. This effect is stressed for systems operating under less constrained image acquisition setups and protocols, due to higher variations in the amounts of captured data. Our experiments led us to conclude that the utility of the image interpolating methods is directly corresponding to the levels of noise that images contain.

Teaching History

  • 2011 2010

    Internet Technologies

    Practical classes on Internet Technologies for the courses of Computer Science and Engineering (BSc) and Sports Sciences (BSc). Technologies and methodologies used: PHP, HTML, JavsScript, CSS and Apache.

  • 2011 2009

    Databases

    Practical classes on Databases for the courses of Computer Science and Engineering (BSc) and Information Systems Technologies (BSc). Technologies and methodologies used: MySQL, PHP, HTML and Apache.

@ SOCIA Lab.

You can also visit the SOCIA Lab, located at University of Beira Interior, Room 612 (Department of Computer Science).

Lab is open every day from 9:00 until 18:00, but you may consider e-mail me before to fix an appointment.