A Maximum-Likelihood Approach to Symbolic Indirect Correlation

Author

Joshi, Ashutosh ; Nagy, George ; Lopresti, Daniel ; Seth, Sharad

Author_Institution

Rensselaer Polytech. Inst., Troy, NY

Volume

3

fYear

0

fDate

0-0 0

Firstpage

99

Lastpage

103

Abstract

Symbolic indirect correlation (SIC) is a non-parametric method that offers significant advantages for recognition of ordered unsegmented signals. A previously introduced formulation of SIC based on subgraph-isomorphism requires very large reference sets in the presence of noise. In this paper, we seek to address this issue by formulating SIC classification as a maximum likelihood problem. We present experimental evidence that demonstrates that this new approach is more robust for the problem of online handwriting recognition using noisy input

Keywords

isomorphism; maximum likelihood detection; maximum likelihood problem; noisy input; nonparametric method; online handwriting recognition; ordered unsegmented signal recognition; subgraph-isomorphism; symbolic indirect correlation; Engines; Handwriting recognition; Hidden Markov models; Ink; Maximum likelihood estimation; Noise robustness; Pattern matching; Pattern recognition; Silicon carbide; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.97

Filename

1699478