Publication: Camera Based Gesture Commands for Smart Home Applications
Date
2020-02
Authors
Muhammad Firdaus bin Mohd Fauzi
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This thesis focuses on the training process of developing a deep learning model that recognizes five different hand gestures for controlling smart home appliances. The deep learning model is implemented using tensorflow framework and utilizing transfer learning technique. The pre-trained model used for transfer learning is MobileNet. The accuracy of the deep learning model is 94% with validation accuracy of 87%.
Description
FYP 2 SEM 2 2019/2020
Keywords
Tensorflow , deep learning , MobileNet , Transfer Learning