
Jean-Luc DugelayEURECOM · Digital Security Department
Jean-Luc Dugelay
Ph.D. 92 FELLOW IEEE 2012 ICPR 2018
About
376
Publications
139,156
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
8,460
Citations
Introduction
Imaging Security
Additional affiliations
January 1993 - April 2018
September 2016 - present
Institut Mines-Télécom EURECOM
Position
- Professor
Description
- Digital Image Processing; Image & Video Compression; Imaging Security
January 1993 - October 2016
Education
October 1989 - December 1992
Publications
Publications (376)
In recent years, the estimation of biometric parameters from facial visuals, including images and videos, has emerged as a prominent area of research. However, the robustness of deep learning-based models is challenged, particularly in the presence of changing illumination conditions. To overcome these limitations and unlock new opportunities, ther...
Automatic beautification through social media filters has gained popularity in recent years. Users apply face filters to adhere to beauty standards, posing challenges to the reliability of facial images and complicating tasks like automatic face recognition. In this work, the impact of digital beautification is assessed, focusing on the most popula...
Accurate remote pulse rate measurement from RGB face videos has gained a lot of attention in the past years since it allows for a non-invasive contactless monitoring of a subject’s heart rate, useful in numerous potential applications. Nowadays, there is a global trend to monitor e-health parameters without the use of physical devices enabling at-h...
Gradient-weighted Class Activation Mapping (Grad- CAM), is an example-based explanation method that provides a gradient activation heat map as an explanation for Convolution Neural Network (CNN) models. The drawback of this method is that it cannot be used to generalize CNN behaviour. In this paper, we present a novel method that extends Grad-CAM f...
Nowadays, video analysis applications are gaining popularity given the rise of CCTV systems and the availability of video cameras to the general public, such as cameras in mobile devices. Many image analysis and processing tasks have evolved toward video domain, with the advantage of redundant information obtained from several frames, which can hel...
In this chapter, we present the various categories of Face Manipulation and their use within different remote operational systems. We then use the example of remote identity document onboarding systems to illustrate how each category can be used in practice to compromise such a system. After a definition of the different Face Manipulation categorie...
In this paper, we explore whether automatic face recognition can help in verifying widespread misinformation on social media, particularly conspiracy theories that are based on the existence of body doubles. The conspiracy theory addressed in this paper is the case of the Melania Trump body double. We employed four different state-of-the-art descri...
In this paper, a novel image transformation scheme is proposed to protect the visual information. By mimicking an arbitrarily chosen reference image, a secret image is visually changed and can be exactly recovered from the transformed image when needed. Unlike the block-wise visual encryption methods, the proposed transformation scheme modifies the...
The growing interest in exploring thermal face biometrics is mostly due to the robustness of thermal imagery to face spoofing attacks. However, this robustness lies in the acquisition of thermal properties by the thermal sensor and is limited to presentation attacks. In this paper, we propose a new type of attack on thermal face recognition systems...
The ability of Deep Neural Networks (DNNs) to make fast predictions with high accuracy made them very popular in real-time applications. DNNs are nowadays in use for secure access to services or mobile devices. However, as DNNs use increased, at the same time attack techniques are born to “break” them. This paper presents a particular way to fool D...
A technique is put forward to hide data into an animated GIF by exploiting the transparent pixels. Specifically, a new frame is crafted based on the data to be embedded. The newly crafted frame is inserted between 2 existing frames, and the delay time of the affected frames are adjusted accordingly to achieve complete imperceptibility. To the best...
Access to technologies like mobile phones contributes to the significant increase in the volume of digital visual data (images and videos). In addition, photo editing software is becoming increasingly powerful and easy to use. In some cases, these tools can be utilized to produce forgeries with the objective to change the semantic meaning of a phot...
Pervasive and useR fOcused biomeTrics bordEr projeCT (PROTECT) is an EU project funded by the Horizon 2020 research and Innovation Programme. The main aim of PROTECT was to build an advanced biometric-based person identification system that works robustly across a range of border crossing types and that has strong user-centric features. This work p...
Thermal imaging has substantially evolved, during the recent years, to be established as a complement, or even occasionally as an alternative to conventional visible light imaging, particularly for face analysis applications. Facial landmark detection is a crucial prerequisite for facial image processing. Given the upswing of deep learning based ap...
Thermal face image analysis is favorable for certain circumstances. For example, illumination-sensitive applications, like nighttime surveillance; and privacy-preserving demanded access control. However, the inadequate study on thermal face image analysis calls for attention in responding to the industry requirements. Detecting facial landmark poin...
Common sense usually considers the assessment of female human attractiveness to be subjective. Nevertheless, in the past decades, several studies and experiments showed that an objective component in beauty assessment exists and can be strictly related, even if it does not match, with proportions of features. Proportions can be studied through anal...
Generating visible-like face images from thermal images is essential to perform manual and automatic cross-spectrum face recognition. We successfully propose a solution based on cascaded refinement network that, unlike previous works, produces high quality generated color images without the need for face alignment, large databases, data augmentatio...
This paper presents a novel dataset for image and
face manipulation detection and localization called DEFACTO.
The dataset was automatically generated using Microsoft common object in context database (MSCOCO) to produce semantically meaningful forgeries. Four categories of forgeries have
been generated. Splicing forgeries which consist of insertin...
We introduce, in this paper, a new scheme of score level fusion for face authentication from visible and thermal face data. This proposed scheme provides a fast and straightforward integration into existing face recognition systems and does not require recollection of enrollment data in thermal spectrum. In addition to be used as a possible counter...
The term “plenoptic” comes from the Latin words plenus (“full”) + optic. The plenoptic function is the 7-dimensional function representing the intensity of the light observed from every position and direction in 3-dimensional space. Thanks to the plenoptic function it is thus possible to define the direction of every ray in the light-field vector f...
Face synthesis from thermal to visible spectrum is fundamental to perform cross-spectrum face recognition as it simplifies its integration in existing commercial face recognition systems and enables manual face verification. In this paper, a new solution based on cascaded refinement networks is proposed. This method generates visible-like colored i...
1. To answer affirmatively to the question of whether one can use reference PRNU fingerprint extracted from images, known to be of superior quality, to identify a video source smartphone.
2. To find the optimal parameters for a higher identification rate.
To address the issues like identity theft and security threats, a continuously evolving technology known as biometrics is presently being deployed in a wide range of personal, government, and commercial applications. Despite the great progress in the field, several exigent problems have yet to be addressed to unleash biometrics full potential. This...
The prevalent commercial deployment of mobile biomet-rics as a robust authentication method on mobile devices has fueled increasingly scientific attention. Motivated by this, in this work we seek to provide insight on recent development in mobile biometrics. We present parallels and dissimilarities of mobile biometrics and classical biomet-rics, en...
Although visible face recognition systems have grown as a major area of research, they are still facing serious challenges when operating in uncontrolled environments. In attempt to overcome these limitations, thermal imagery has been investigated as a promising direction to extend face recognition technology. However, the reduced number of databas...
This work presents a novel multimodal database comprising 3D face, 2D face, thermalface, visible iris, finger and hand veins, voice and anthropometrics. This dataset will constitute avaluable resource to the field with its number and variety of biometric traits. Acquired in the con-text of the EU PROTECT project, the dataset allows several combinat...
Here, the authors propose a scalable scrambling algorithm operating in the discrete cosine transform (DCT) domain within the JPEG codec. The goal is to ensure that people are no more identifiable while keeping their actions still understandable regardless of the image size. For each 8 × 8 block, the authors encrypt the DCT coefficients to protect d...
Smartphones are increasingly becoming a tool for ubiquitous access to a number of services including, but not limited to, e-commerce and home banking, and are used more and more for sensitive data storage. If, on one hand, this makes the smartphone a powerful tool in our private and professional life, on the other hand it has brought about a series...
Convolutional Neural Networks (CNNs) have been proven very effective for human demographics estimation by a number of recent studies. However, the proposed solutions significantly vary in different aspects leaving many open questions on how to choose an optimal CNN architecture and which training strategy to use. In this work, we shed light on some...
Information plays a key role in the management of natural disasters and relief organization. Current light UAVs can help improve the assessment of the situation. They relieve the rescue teams of data collection tasks, which remain a long process. At the same time, these drones can take part in search operations thanks to their autonomy and their ad...
To address the issues like identity theft and security threats, a continuously evolving technology known as biometrics is presently being deployed in a wide range of personal, government, and commercial applications. Despite thegreat progress in the field, several exigent problems have yet to be addressed to unleash biometrics full potential. This...
Light field cameras are emerging as powerful devices to capture rich scene representations that provide unique advantages for analysis and representation purposes. Some recent works have shown the power and usefulness of the richer information carried out by light field imaging, notably for face recognition. However, it is still difficult to fully...
It has been recently shown that Generative Adversarial Networks (GANs) can produce synthetic images of exceptional visual fidelity. In this work, we propose the GAN-based method for automatic face aging. Contrary to previous works employing GANs for altering of facial attributes, we make a particular emphasize on preserving the original person's id...
FIRE is a Fast Iris REcognition algorithm especially designed for iris recognition on mobile phones under visible-light. It is based on the combination of three classifiers exploiting the iris colour and texture information. Its limited computational time makes FIRE particularly suitable for fast user verification on mobile devices. The high parall...
Information plays a key role in the management of natural disasters and relief organization. Current light UAVs can help improve the assessment of the situation. They relieve the rescue teams of data collection tasks, which remain a long process. At the same time, these drones can take part in search operations thanks to their autonomy and their ad...