Title :
An efficient method for tuning handwriting parameters
Author :
Hullender, Gregory N.
Author_Institution :
Microsoft Corp., Redmond, WA, USA
fDate :
6/23/1905 12:00:00 AM
Abstract :
Many problems in recognition involve making linear combinations of results from various experts. Computing the coefficients can be expensive because a single test run can take many minutes, hours, or even days, and many values need to be evaluated to find an optimum. This paper describes an algorithm that can make a good approximation to the optimum value for a parameter in a single pass over the tuning data and also outlines methods for tuning several parameters at once
Keywords :
handwriting recognition; handwritten character recognition; Microsoft Japanese online handwriting recognition system; handwriting parameters tuning; single pass; single test run; Approximation algorithms; Character recognition; Handwriting recognition; Heart; Histograms; Ink; Neural networks; Prototypes; Spatial databases; Testing;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953793
