Tools
Tools
Babu, Ibrahim Rinub (2022) Implementation of Touch-less Hand Gesture Recognition ATM Based on Deep Learning Approach. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Many people are concerned that they will contract coronavirus disease if they use ATM’s during the outbreak. Corona and other air-born viruses have been shown to linger on ATM screens or buttons for up to 72 hours, with the potential to trigger a pandemic outbreak. The goal of this research is to review all the current architectures and methodologies to come up with a better Deep learning neural network architecture for hand gesture recognition. The best model is combined with an ATM online application simulator, which allows all financial transactions to be completed using gestures and financial transactions to be authenticated using the user’s facial recognition, allowing for complete contactless management of the ATM application. In this study, Custom CNN models and transfer learning models such as VGG-16, ResNets50, and MobileNet were created and evaluated using various metrics with the precision of 92.99 percent, 99.04 percent, 99.14 percent, and 99.65 percent. The ResNet50 with the processing time of 26ms with the real-time validation precision of 100
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Banking 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 Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 17 Jan 2023 17:46 |
| Last Modified: | 07 Mar 2023 11:04 |
| URI: | https://norma.ncirl.ie/id/eprint/6076 |
Actions (login required)
 |
View Item |