Crisp and Fuzzy Evaluations and D.P. Algorithms for Dealing with Extra Ink in Cursive Handwriting Recognition

Abstract

In segmentation-by-recognition methods, words are 1-ecognised by searching for the aggregation of basic segments (strokes) that best matches one of the sequences of letters allowed by the lexicon. The presence of spurious strokes (“extra ink”) impairs recognition, since they have to be associated anyway with some letter of the word. This paper describes how… (More)
DOI: 10.1109/ICPR.2000.902856

Topics

2 Figures and Tables

Slides referencing similar topics