Tools
Tools
Malik, Monika (2022) Sign Language Detection using Deep Learning Architecture in Cloud computing Environment. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (681kB) | Preview |
Abstract
In order to facilitate the deaf community and general public, the usage of signlanguage detector plays an important role. However, detecting the hand gesture movements in real-time is a challenging task and still an open area of research. Deep learning based architecture has provided significant outcomes in terms of pattern recognition, image processing and object detection. Therefore, in this work we have 4 different deep learning based neural network architectures. Among them VGG-19 and ResNet-50 are the transfer learning models and 3-Layer and 5-layers of convolutional architecture are the custom models. After evaluating the results over the test data based on accuracy, loss, precision, recall and F1-score, we have obtained the better outcomes using 5-layers of Convolutional architecture for Sign language detection.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Semiotics > Language. Linguistic theory > Gesture. Sign language Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Cloud Computing |
| Depositing User: | Tamara Malone |
| Date Deposited: | 02 Dec 2022 15:34 |
| Last Modified: | 08 Mar 2023 14:48 |
| URI: | https://norma.ncirl.ie/id/eprint/5958 |
Actions (login required)
 |
View Item |