Tools
Tools
Mehatari, Bharti (2022) Hand Gesture Recognition and Classification using Computer Vision and Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (908kB) | Preview |
Abstract
Hand gesture recognition systems have gained a huge momentum in the field of computer vision over the last few decades having its application in various fields. Considering the recent pandemic situation, the need for touch-less devices have become key concern for people’s hygiene and safety. Also, the idea of devices that function via hand gestures have also attracted people to adopt such technology thus creating a demand of gesture recognition systems in the market. Recent research has shown the dominance of deep learning algorithms on feature analysis and image classification. Therefore, these techniques have been developed in this research project, to create models that can detect and identify gestures used on a daily basis. The dataset consists of ten different individuals performing various gestures. The implementation also demonstrated several image processing operations such as smoothing of images, greyscale image conversion, image thresholding as well as data augmentation. The hyperparameter optimised 2D convolution model outperformed other implemented models that provided highest accuracy of 99.88% and only 7 cases misclassified out of 20000 images. The confusion matrix and learning curve were also considered for the performance evaluation.
| 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 |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 23 Feb 2023 11:59 |
| Last Modified: | 02 Mar 2023 09:23 |
| URI: | https://norma.ncirl.ie/id/eprint/6225 |
Actions (login required)
 |
View Item |