magistrsko delo
Abstract
V magistrskem delu je predstavljen proces izdelave in optimizacije 3D navideznega tolmača slovenskega znakovnega jezika za namen polavtomatiziranega tolmačenja za omejeno besedišče z uporabo aplikacijskih vmesnikov. Okolje Blender omogoča izdelavo naprednih fotorealističnih 3D modelov, okoščevanje in animacijo le-teh, ter upravljanje vnaprej pripravljenih akcij s pomočjo Python aplikacijskega vmesnika. Zaradi želje, da bi se upodabljanje čim bolj približalo realnemu času, je bilo v procesu izdelave izvedenih več optimizacij, tako na poligonski mreži, okostju za učinkovitejše upravljanje modela, prilagoditvi programskega vtičnika, kakor tudi optimizacija nastavitev pogonov za upodabljanje in analiza hitrosti upodabljanja na različni strojni opremi.
Za povečanje dostopnosti, še posebej v primerih izrednih razmer, kot je izbruh pandemije COVID-19, je lahko uporaba 3D navideznega tolmača uporabna alternativa. Zaradi relativno visokih zahtev gluhe skupnosti, da morajo navidezni tolmači delovati čim bolj naravno, brez zatikanja, nepotrebnega vračanja v nevtralni položaj, ter uporabljati izrazito obrazno mimiko, izdelava primerne rešitve zahteva poglobljeno analizo vseh ključnih področij magistrske naloge. Končne upodobitve v praktičnem delu so se izkazale za uspešne, saj so vsi uporabniki v preliminarni študiji brez težav razumeli vse odkretane pojme. Končna zasnova bi lahko bila uporabljena na več različnih področjih, v sodelovanju z gluho skupnostjo pa tudi kot polavtomatski prevajalnik slovenskega govornega v znakovni jezik.
Keywords
dostopnost;znakovni jezik;tolmačenje;3D modeliranje;animacija;Python API;Blender;multimedija;računalništvo;magisteriji;
Data
Language: |
Slovenian |
Year of publishing: |
2021 |
Typology: |
2.09 - Master's Thesis |
Organization: |
UL FE - Faculty of Electrical Engineering |
Publisher: |
[Ž. Juvan] |
UDC: |
004.94:81'221(043.2) |
COBISS: |
79777795
|
Views: |
245 |
Downloads: |
71 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
Animated slovenian sign language interpreter for a limited vocabulary |
Secondary abstract: |
In the master thesis the process of creation and optimization of a 3D virtual interpreter of Slovenian Sign Language is presented, intended for semi-automated interpretation for a limited vocabulary with usage of Application Programming Interfaces. The Blender environment enables the creation, rigging and animation of advanced photorealistic 3D models, as well as the management of pre-prepared actions using Python API. Due to the goal to bring final renders as close as possible to real time rendering, several optimizations were performed, from optimization of the polygon mesh, the created rig for more efficient movement, created API adjustments, as well as an optimisation of the render engine settings and analysis of render speed on different hardware equipment.
The use of a 3D virtual interpreter can be a useful alternative to increase accessibility, especially in emergencies, such as the outbreak of the COVID-19 pandemic. Due to the relatively high demands of the deaf community which requires virtual interpreters to move as naturally as possible, with smooth gestures and without unnecessary returns to a neutral position, and to show eloquent facial expressions, the creation of an appropriate solution requires in-depth analysis of all key areas of the master thesis. The final renders in the practical part proved to be successful, as all users in the preliminary study easily understood all animated signed sentences. The final creation could be used in several different domains, while it could also be utilised, in collaboration with the deaf community, as a semi-automatic translator of spoken Slovenian to sign language. |
Secondary keywords: |
accessibility;sign language;interpretation;3D modeling;animation;Python API;Blender;multimedia;computer science;master's degree;Slovenski znakovni jezik;Računalniška simulacija;Računalniška animacija;Računalništvo;Univerzitetna in visokošolska dela; |
Type (COBISS): |
Master's thesis/paper |
Study programme: |
1001017 |
Thesis comment: |
Univ. v Ljubljani, Fak. za računalništvo in informatiko |
Pages: |
115 str. |
ID: |
13587580 |