AbstractThese years, a field of study derived from artificial intelligence makes a lot of noise. It is the deep learning. These methods revolutionizes various domains due to its robustness when treating unstructured data such as images, sounds or video. Applying those new methods to sign language recognition could be valuable for the integration of deaf or hard of hearing people in our societies. To do that, the laboratories of french Belgian sign language (LSFB-lab) shared its expertise and provided us an important corpus of sign language.
This work aims to identify all the methods useful for solving this task and test them. The output of this research is a software architecture facilitating the setup of experimentation and the reuse of their components in order to create more easily other experimentation. This architecture may be used in the future to build and compare the various methods identified.
|Date of Award||14 Jun 2019|
|Supervisor||Anthony Cleve (Supervisor) & BENOIT FRENAY (Co-Supervisor)|
- video recognition
Design and Testing of an Architecture for Deep Learning Experiments Applied to Sign Language Recognition
Fink, J. (Author). 14 Jun 2019
Student thesis: Master types › Master in Computer Science Professional focus in Data Science