Graduate School and Research Center in Digital Sciences


Eurecom - Digital Security 
04 93 00 81 41
04 93 00 82 00


  • He is currently with the EURECOM, Digital Security dept. as a Professor
  • He teaches Image and Video Processing and Coding, and Imaging for Security Applications (Watermarking, Steganography, Biometrics, Video surveillance and Forensics)

My courses

  • ImCod / Fall 2017 - Image & Video Compression

    Because multimedia data (in particular image and video) require efficient compression techniques in order to be stored and delivered, image and video compression is a crucial element of an effective communication system.

    This course covers the most popular lossless and lossy formats, introduces the key techniques used in source coding, as well as appropriate objective/subjective metrics for visual quality evaluation.

    Teaching and Learning Methods: Each class includes a problem session for students to practice the material learned. This course includes a limited number of lab session hours.

    Course Policies: It is mandatory to attend lab. sessions.

  • ImProc / Fall 2017 - Digital Image Processing

    The course aims at providing students with a basic knowledge and practice about the use of computer algorithms to perform image processing on digital images. The two main objectives attached to Digital Image Processing (DIP) are to improve the visual quality of images and to automatically extract semantic information from visual data (e.g. object recognition). 

    Teaching and Learning Methods: Each session is split into two parts: 1.5-hour lecture and 1.5-hour lab.

     Course Policies:  It is mandatory to attend lab. sessions.

  • ImSecu / Spring 2018 - Imaging Security

    Image & Video processing is part of many applications related to security: digital watermarking, steganography, image forensics, biometrics, and video surveillance.

    • Digital Watermarking allows owners or providers to hide an invisible and robust message inside a digital Multimedia document, mainly for security purposes such as owner or content authentication. There is a complex trade-off between the different parameters : capacity, visibility and robustness.
    • Steganographyis the art and science of writing hidden messages (in a picture or a video) in such a way that no-one apart from the sender and intended recipient even realizes there is a hidden message.
    • Image Forensics includes two main objectives: (1) To determine through which data acquisition device a given image is generated; (2) To determine whether a given image has undergone any form of modification or processing.
    • Biometrics: The security fields uses three different types of authentication : something you know, something you have, ore something you are : a biometric. Common physical biometrics includes fingerprints, hand geometry ; and retina, iris or facial characteristics. Behavioural characters include signature, voice. Ultimately, the technologies could find their strongest role as intertwined and complementary pieces of a multifactor authentication system. In the future biometrics is seen playing a key role in enhancing security, residing in smart cards and supporting personalized Web e-commerce services. Personalization through person authentication is also very appealing in the consumer product area. This course will focus on enabling technologies for Biometrics, with a particular emphasis on person verification and authentication based on or widely using image/video processing.
    • Video surveillance is the monitoring of the behavior, activities, or other changing information, usually of people for the purpose of influencing, managing, directing, or protecting. By default, for a better scene understanding, automatic image processing tools are used between acquisition/transmission and visualization or storage

    Teaching and Learning Methods: Ce cours comporte un nombre limité de Travaux Pratiques et Travaux Dirigés.


    Course Policies: Les TPs sont obligatoires.



  • In June 2016, he has received with his PhD student Grégory Antipov, a double Award (Best Paper Award and 1st Place Award) for their paper "Apparent Age Estimation from Face Images Combining General and Children-Specialized Deep Learning Models" (IEEE CVPR).
  • In November 2013, he has received with his co-authors Xuran Zhao and Nicholas Evans, a Best Student Paper Award for the article "Unsupervised multi-view dimensionality reduction with application to audio-visual speaker retrieval".
  • He received the Fellow Distinction from IEEE in 2012.
  • In July 2011, he was awarded a Best Presentation Award (with Antitza Dantcheva) for the article "Female facial aesthetics based on soft biometrics and photo-quality"
  • He was awarded the SEE 2010 Blondel Medal for his outstanding work in biometrics and digital watermarking.