Paper Info
Title
Data Compression Of Digital-Ink With Pen-Slips Using Multi-Level L-1 Smoothing Splines
Abstract
In this paper, we consider a problem on data compression of "Digital-Ink" which is a sequence of position data sampled from the traced curve at a sampling rate. Here we suppose that a set of digital-ink is measured and stored by electronic device (e.g. smart-phone and pen-tablet PC, etc.) and that ink data include sudden deviations corresponding to pen slips during the handwriting input due to a frictionless sheet on the display, etc. For such a problem, we here develop a robust method of digital-ink compression by employing multi-level L-1 smoothing spline method based on B-splines, where the term 'multi-level' indicates that not only the measured digital ink data (i.e. position data) but also its derivatives (i.e. velocity and acceleration data) are considered. Then, it is shown that multi-level L-1 smoothing splines can be used effectively for excluding the influence due to the pen slips. The effectiveness and usefulness are examined by some experimental studies.
Year
DOI
Venue
2015
10.1109/SMC.2015.313
2015 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2015): BIG DATA ANALYTICS FOR HUMAN-CENTRIC SYSTEMS
Keywords
Field
DocType
Data compression, Digital-Ink, pen-slip, multi-level L-1 smoothing spline, B-splines
Computer vision,Thin plate spline,Inkwell,Computer science,Smoothing spline,Sampling (signal processing),Robustness (computer science),Smoothing,Acceleration,Artificial intelligence,Data compression
Conference
ISSN
Citations 
PageRank 
1062-922X
0
0.34
References 
Authors
4
3
Name
Order
Citations
PageRank
Yuta Mieno100.68
Hiroyuki Fujioka23713.37
Hiroyuki Kano37519.05