1. Gesture recognition system based on restricted Boltzmann machine.
- Author
-
Meena, S. Divya, Rao, Thoom Purna Chander, Chetty, B. Meghna, Nouluri, Vamsi Krishna, Cilagani, Meghana Nagaraj, Aashitha, Kanagala, and Sheela, J.
- Subjects
- *
BOLTZMANN machine , *GESTURE , *FEATURE extraction , *CARDIAC imaging , *SENSOR networks - Abstract
The hand is a non-rigid item with many motions, making gesture identification more complex. The classification and recognition of single-frame still images lie at the heart of dynamic gesture recognition. As a result, this paper focuses mostly on static gesture identification. There are currently various issues with gesture recognition, including as accuracy, real-time capability, and resilience. To address the aforementioned issues, this research proposes a gesture recognition network that combines CNN and RBM. It primarily employs asuperposed network of numerous RBMs for unsupervised feature extraction, which is then merged with CNN supervised feature extraction. These two characteristics are then combined to classify them. The simulation findings suggest that the proposed superposed network performs better in detecting simple and complex backdrop gesture samples, and that gesture sample detection in complex backgrounds still needs to be improved. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF