Advanced techniques for digital imaging

Catalogue of disciplines

Overview

Master's degree program "Advanced Imaging Techniques Digital Imaging" (TAID) program responds to the current development and evolution requirements of IT&C services economy, in the context of the generalization production and exploitation of digital images. The fields of activity concerned are virtually unlimited, ranging from 'consumer' applications (camera technologies and smartphone mobile terminals), the medical field (products and medical image analysis and processing technologies), military (products and technologies for satellite image processing), the security (surveillance and biometric systems), surveillance industrial automation (product inspection systems), robotics (product inspection human-machine interface systems) and many others.

The training is based on the application of programming techniques, algorithmic and machine learning.

Potential employers target both academia (teaching and research) as well as industrial R&D environments such as organizations/firms of any size, from small (e.g. start-ups and spin-off) to multinationals.

Who is it for?

The master program is mainly addressed to engineers in the fields of Computer and Information Technology, Electronic Engineering, Telecommunications and Information Technologies, Applied Engineering Sciences, Engineering Systems Engineering. The program may also be taken by graduates with degrees in Mathematics, Computer Science or Cybernetics.

Objectives of the Master's programme

The TAID master's program aims to train licensed engineers so as to enable them to model and design software/hardware systems for image processing and analysis and computer vision for specific applications, as well as the ability to identify and analyze specific problems and develop strategies for solving them them.

Specialist skills offered to graduates

The competences recognised by the RNCIS and listed in the diploma supplement are:

• Thorough knowledge of the concepts, principles and methodologies of design specific to the fields of image analysis and processing and their applications;
• Ability to design and implement, as well as test and evaluate complex image processing and analysis systems;
• Ability to create and implement mathematical models appropriate to concepts specific to image processing and analysis;
• Ability to model and implement the software components of a image processing and analysis applications for different systems (Windows/Android);
• Design and realization of advanced database applications (data mining, database theory and design, including distributed multimedia technologies).

Examples of research directions addressed

The titles of the dissertations in progress over the last two years are a edifying example of the complexity and topicality of the themes addressed in the TAID Master's program:

• Automated algorithms for tracking people and their behavior in video streams
• Digital image reframing algorithms based on automatic analysis of content analysis
• Distributed application for image styling
• Detection of objects of interest in thermal images acquired with telephoto optics using deep neural networks
• Automatic analysis of facial expressions in children
• Duplicate detection of digital color images in a database multimodal
• Facial analysis for automatic sibling recognition
• Recommendation system for a multimedia platform
• Distributed localization solution based on content similarity in images
• Automatic face rejuvenation/aging system
• Android application for displaying and transmitting image information digital mammography images
• Simulated expression detection
• Vehicle detection from natural images using convolutional networks
• Using the three-dimensional discrete cosine transform in video compression
• Method for tracking pedestrians in image sequences
• Detection of light signals (traffic lights, cars) in sequences video
• Detection of acquired digital images with finger-in-finger degradations in front of the lens
• Intelligent traffic light system for an intersection
• Facial analysis method for recognizing emotions in sequences of images
• Automatic traffic monitoring: traffic jam detection and prediction of accidents
• Comparative evaluation between SDKs for dedicated neural networks mobile platforms
• Combining colors in fashion design and aesthetics using networks convolutional colorization neural networks
• Efficient analysis of facial expressions
• Neural network optimization for integrated circuit applications
• Unsupervised information extraction method for improving emotion recognition in facial images
• Denoising and sharpening using U-Net architecture
• Study on the efficiency of a convolutional network to detect points points on the human face
• Facial expression transfer
• Facial recognition authentication service