2 |
Automatische Gebärdenspracherkennung: Von Videokorpora zu Glossensätzen ... : Automatic sign language recognition : from video corpora to gloss sentences ...
|
|
|
|
Abstract:
Dissertation, RWTH Aachen University, 2020; Aachen 1 Online-Ressource (xiii, 155 Seiten) : Illustrationen, Diagramme (2020). = Dissertation, RWTH Aachen University, 2020 ... : This PhD thesis investigates large vocabulary, continuous automatic sign language recognition (ASLR) from single view video using hidden Markov models (HMMs) with Gaussian mixture models (GMMs) as state emission functions and n-gram, statistical language models. We go beyond the state-of-the-art by investigating continuous sign language instead of isolated signs and extract features and object locations from video via object tracking foregoing invasive data acquisition methods such as bulky cyber gloves. Overall, we make contributions in three major areas. In the first part of this thesis, we develop best practices for sign language corpus creation and introduce the large vocabulary, single view, continuous sign language corpus RWTH-PHOENIX-Weather which has been created in the context of this work. RWTH-PHOENIX-Weather is annotated in gloss notation and features several subsets usable for object tracking, single signer as well as multi signer recognition. The second part of this thesis focuses on object ...
|
|
Keyword:
hidden markov model; large vocabulary; modality combination; sign language; statistical recognition from video
|
|
URL: https://dx.doi.org/10.18154/rwth-2020-08775 https://publications.rwth-aachen.de/record/796101
|
|
BASE
|
|
Hide details
|
|
3 |
Comparison of Machine Learning Models: Gesture Recognition Using a Multimodal Wrist Orthosis for Tetraplegics
|
|
|
|
In: The Journal of Purdue Undergraduate Research (2020)
|
|
BASE
|
|
Show details
|
|
|
|