Design and evaluation of a process for training categorization models from synthetic data


Claudine Combe
Herve Poirier

Duration: 4-6 months
Start Date: Q1 2016

The Xerox Research Centre Europe (XRCE) has a strong expertise in Image Understanding, applied with success in domains such as parking automation or traffic rules enforcement. Automating such image analysis is obtained by the use of machine learning algorithms, with the need of labelled images to construct the necessary models.

The internship proposal aims at designing and developing a process to learn a recognition model for a new object from a 3D model of the object. Using synthetic data in machine learning has several advantages: it reduces the task of manual annotations and a large amount of images can be created through the simulation of the real world environment (illumination changes, points of view…). The major goal of this project is to compare the performances of recognition models trained on synthetic data from models trained on real world data, as well as evaluating the amount of work required to train a new object.

In this internship, the intern will focus on some of the following tasks in collaboration with the other team members:

  • Evaluate 3D scanning technologies and design simple 3D models of objects
  • Extract 2D images after transformations (lights, points of view) and create a database of synthetic images
  • Generate the input parameters for the training system
  • Evaluate the performances of the generated model against a model trained on real world data.

The intern will be part of a team of developers and researchers. XRCE projects are managed with an agile methodology which allow interns to follow all the steps of software development, including research, design, implementation, test and integration.

Candidates will be:

  • Students in Computer Sciences Engineering\Bsc\Masters
  • Strong knowledge AND practice of Object Oriented Programming: C++ and Java in particular
  • Knowledge in 3D engines, 3D rendering and simulation
  • Knowledge in computer vision and machine learning techniques
  • Knowledge in Agile methodologies and Test Driven Development is a plus

During her/his internship the candidate will acquire a significant knowledge in advanced computer vision and machine learning techniques while working closely with researchers and engineers. Additionally, the candidate will become knowledgeable of Agile methodologies (eg: SCRUM, Continuous Integration)

Discover in this video  what it’s like to work at Xerox Research Centre Europe.

Xerox Research Centre Europe (XRCE) is a young, dynamic research organization, which creates innovative technologies to support growth in Xerox business process outsourcing and document management services businesses.

Our domains of research stretch from the social sciences to computer science. We have renowned expertise in machine learning, natural language processing, computer vision, ethnography and services computing.

XRCE is part of the Xerox Innovation group  made up of 650 researchers and engineers in four world-renowned research and technology centres. Our goal is to make Xerox a great place to work. Through a comprehensive set of employee-focused initiatives, we promote diversity by nurturing a culture of inclusion and opportunity, and through measurable actions.


Xerox complies with Equal Employment Opportunity (EEO) guidelines. Xerox does not discriminate on the basis of race, colour, religious belief, sex, age, national origin, citizenship status, marital status, union status, sexual orientation, gender identity or individuals with a disability. Our main building is compliant with the AGEFIPH  standards for disabled access.

The Grenoble site is set in a park in the heart of the French Alps in a stunning location only a few kilometers from the city centre. The city of Grenoble has a large scientific community made up of national research institutes (CNRS, Universities, INRIA) and private industries. Stimulated also by the presence of a large student community, Grenoble has become a resolutely modern city, with a rich heritage and a vibrant cultural scene. It is a lively and cosmopolitan place, offering a host of leisure opportunities. Winter sports resorts just half an hour from campus and three natural parks at the city limits make running, skiing, trekking, climbing and paragliding easily available.
Grenoble is close to both the Swiss and Italian borders.
AEPI, the Grenoble-Isere Economic Development Agency: "Grenoble-Isere, the place to innovate, where the only limit is your imagination."

Xerox Search Opportunities