For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Air-Writing Recognition Based on Fusion Network for Learning Spatial and Temporal Features
Buntueng YANA Takao ONOYE
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2018/11/01
Online ISSN: 1745-1337
Type of Manuscript: Special Section PAPER (Special Section on Smart Multimedia & Communication Systems)
Category: Neural Networks and Bioengineering
air-writing recognition, human-machine interface, recurrent neural network, convolutional neural network, fusion network,
Full Text: PDF(930.2KB)>>
A fusion framework between CNN and RNN is proposed dedicatedly for air-writing recognition. By modeling the air-writing using both spatial and temporal features, the proposed network can learn more information than existing techniques. Performance of the proposed network is evaluated by using the alphabet and numeric datasets in the public database namely the 6DMG. Average accuracy of the proposed fusion network outperforms other techniques, i.e. 99.25% and 99.83% are observed in the alphabet gesture and the numeric gesture, respectively. Simplified structure of RNN is also proposed, which can attain about two folds speed-up of ordinary BLSTM network. It is also confirmed that only the distance between consecutive sampling points is enough to attain high recognition performance.