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.
Quantitative Analyses on Effects from Constraints in Air-Writing
Songbin XU Yang XUE Yuqing CHEN
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2019/04/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
inertial sensor, air-writing recognition, quantitative analyses, LSTM-RNN,
Full Text: FreePDF(2.4MB)
Very few existing works about inertial sensor based air-writing focused on writing constraints' effects on recognition performance. We proposed a LSTM-based system and made several quantitative analyses under different constraints settings against CHMM, DTW-AP and CNN. The proposed system shows its advantages in accuracy, real-time performance and flexibility.