Integrating weighted LCS and SVM for 3D handwriting recognition on handheld devices using accelerometers

Authors:
Wang-Hsin Hsu;Yi-Yuan Chiang;Jung-Shyr Wu
Affiliations:
Department of Computer Science and Information Engineering, Vanung University, Chungli, Taoyuan, Taiwan and Department of Electrical Engineering, National Central University, Chungli, Taoyuan, Tai ...;Department of Computer Science and Information Engineering, Vanung University, Chungli, Taoyuan, Taiwan;Department of Electrical Engineering, National Central University, Chungli, Taoyuan, Taiwan
Venue:
WSEAS Transactions on Computers
Year:
2010

Citing 8
Cited 1

Introduction to algorithms

Introduction to algorithms
The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
The String-to-String Correction Problem

Journal of the ACM (JACM)
An introduction to ROC analysis

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Weighted LCS

Combinatorial Algorithms
Gesture Recognition: A Survey

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A sequence-action recognition applying state machine for user interface

IEEE Transactions on Consumer Electronics

Most discriminating segment - Longest common subsequence (MDSLCS) algorithm for dynamic hand gesture classification

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Based on accelerometer, we propose a 3D handwriting recognition system in this paper. The system is consists of 4 main parts: (1) data collection: a single tri-axis accelerometer is mounted on a handheld device to collect different handwriting data. A set of key patterns have to be written using the handheld device several times for consequential processing and training. (2) data preprocessing: time series are mapped into eight octant of three-dimensional Euclidean coordinate system. (3) data training: weighted LCS and SVM are combined to perform the classification task. (4) pattern recognition: using the trained SVM model to carry out the prediction task. To evaluate the performance of our handwriting recognition model, we choose the experiment of recognizing a set of English words. The accuracy of classification could be achieved at about 96.85%.