I-Vector Modeling of Gestures in Automated Sign Language Recognition
Riferimenti PAOLO ERNESTO PRINETTO
Riferimenti esterni TIOTTO Gabriele (PhD)
Gruppi di ricerca TESTGROUP - TESTGROUP
Tipo tesi EXPERIMENTAL
Descrizione The thesis aims at applying models used in speech recognition to the Sign Language recognition. The student will study algorithms for feature extraction of movements from video frames. An architecture will be designed, based on the extraction of parameters (i-vectors) from a low dimensional space (total variability space).
The goal is to apply and investigate the performance of this architecture in the field of signer's image recognition.
Conoscenze richieste Programming Languages: C, C++, Python, Java.
Scadenza validita proposta 31/12/2012 PROPONI LA TUA CANDIDATURA