Rata.SSR: Data Mining for Pertinent Stroke Recognizers

Chang, Samuel Hsiao-Heng; Plimmer, Beryl; Blagojevic, Rachel

Rata.SSR: Data Mining for Pertinent Stroke Recognizers

Files

095-102.pdf (456.87 KB)

Date

2010

Authors

Chang, Samuel Hsiao-Heng
Plimmer, Beryl
Blagojevic, Rachel

Publisher

The Eurographics Association

Abstract

While many approaches to digital ink recognition have been proposed, most lack flexibility and adaptability to provide acceptable recognition rates across a variety of problem spaces. Time and expert knowledge are required to build accurate recognizers for a new domain. This project uses selected algorithms from a data mining toolkit and a large feature library, to compose a tailored software component (Rata.SSR) that enables single stroke recognizer generation from a few example diagrams. We evaluated Rata.SSR against four popular recognizers with three data sets (one of our own and two from other projects). The results show that it outperforms other recognizers on all tests except recognizer and data set pairs (e.g. PaleoSketch recognizer and PaleoSketch data set) in these cases the difference is small, and Rata is more flexible. We hence demonstrate a flexible and adaptable procedure for adopting existing techniques to quickly generate accurate recognizers without extensive knowledge of either AI or data mining.

        @inproceedings{:10.2312/SBM/SBM10/095-102
,
booktitle = {Eurographics Workshop on Sketch-Based Interfaces and Modeling
},
editor = {Marc Alexa and Ellen Yi-Luen Do
},
title = {{Rata.SSR: Data Mining for Pertinent Stroke Recognizers
}},
author = {Chang, Samuel Hsiao-Heng and 
Plimmer, Beryl and 
Blagojevic, Rachel
},
year = {2010
},
publisher = {The Eurographics Association
},
ISSN = {1812-3503
},
ISBN = {978-3-905674-25-5
},
DOI = {/10.2312/SBM/SBM10/095-102
}
}