ISSN:
1432-1769
Keywords:
Handwriting recognition
;
Neural networks
;
Cursive script
;
Hidden Markov models
;
Dictionary search
Source:
Springer Online Journal Archives 1860-2000
Topics:
Computer Science
Notes:
Abstract We present a writer-independent system for online handwriting recognition that can handle a variety of writing styles including cursive script and handprinting. The input to our system contains the pen trajectory information, encoded as a time-ordered sequence of feature vectors. A time-delay neural network is used to estimate a posteriori probabilities for characters in a word. A hidden Markov model segments the word in a way that optimizes the global word score, using a dictionary in the process. A geometrical normalization scheme and a fast but efficient dictionary search are also presented. Trained on 20 k words from 59 writers, using a 25 k-word dictionary, our system reached recognition rates of 89% for characters and 80% for words on test data from a disjoint set of writers.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF01219589
Permalink
