Apply now »
Location: 

Kortrijk, BE

Date:  Nov 24, 2022
Job ID:  7681

Internship: AI-based color rendering profile generation

Barco designs technology that makes everyday life a little better. Seeing beyond the image, we develop sight, sound, and sharing solutions to help you work together, share insights, and wow audiences. Our focus is on three core markets: Enterprise (from meeting and control rooms to corporate spaces), Healthcare (from the radiology department to the operating room), and Entertainment (from movie theaters to live events and attractions). Our solutions make a visible impact, allowing people to enjoy compelling entertainment experiences; to foster knowledge sharing and smart decision-making in organizations and to help hospitals provide their patients with the best possible healthcare. Headquartered in Kortrijk (Belgium), Barco realized sales of 804 million euro in 2021 and has a global team of 3,000+ employees, whose passion for technology is captured in +500 granted patents.

Barco  

Barco designs technology that makes everyday life a little better. Seeing beyond the image, we develop sight, sound, and sharing solutions to help customers work together, share insights, and wow audiences. Healthcare is one of the key markets of Barco. For many years Barco has been contributing to improved healthcare by means of solutions in radiology, mammography, surgery, dermatology, dentistry, pathology etc.  

   

Innovation in healthcare  

The Barco Labs Healthcare team is constantly looking for new innovative solutions that push forward the state-of-the-art and can improve healthcare models. This group takes care of the entire innovation cycle: ideation and MVP definition, market evaluation and business case creation, R&D and clinical work for creation of proof of concepts and solutions, market and clinical / regulatory validation of the solutions, business model and business plan creation, up to commercial introduction and early pilot sales.  

  

The task at hand  

Historically, display color rendering profiles are calculated analytically. With the rise of AI, more advanced techniques have become available to tackle this complex problem. In this master theses you will redefine this problem as a machine learnable problem and use a set of loss functions to both define the intended color rendering behavior as well as to impose constraints such as monotonicity. The ML model takes a set of display measurements as input. The model should allow for end-to-end optimization of the image pipeline, taking into account hardware constraints (such as 1D and 3D look-up table sizes). You will also define and implement methods to compare the obtained color rendering profiles, both qualitatively and quantitatively.  

 

Qualifications  

  • Color science skills:  

    • Knowledge of color spaces and color (difference) metrics  

    • Basic understanding of an imaging pipeline, including look-up tables  

  • Machine learning skills: 

    • Python, docker, git, … 

    • ML models basics (model training, loss functions, bias/overfitting, …) 

    • TensorFlow (or PyTorch) 

  • Analytical skills: 

    • Qualitative evaluation of developed algorithms by means of test patterns, small perceptual tests, … 

    • Quantitative evaluation: definition and analysis of metrics to objectively compare results 

  • Fluent communication in English  

 

Furthermore, you should be a student in a technical discipline, eligible to work at our HQ in Kortrijk Belgium.  

Apply now »