  |
|
        |
  |
|
|
 |
 |
 |
  |
 |
 |
 |
Publications |  |
|
|
|
Machine vs Humans in a Cursive Script Reading Experiment without Linguistic KnowledgeAbstract - This paper presents an overview of a dynamic cursive script recognition approach that uses no linguistic constraints. This approach seeks to recognize in cursive script, morphologically and pragmatically coherent sequences of character hypotheses. Its performance is compared with the performance of the best available cursive script recognizers (humans) in a reading experiment where linguistic knowledge is useless. The recognition method uses fuzzy-shape grammars to model the morphological characteristics of conventional letters. These models, called allographs, can be viewed as basic (a priori) knowledge for developing a multi-writer recognition system. Character hypotheses are segmented within a cursive word using a parser for these grammars. Character sequences are then constructed from these segmentation hypotheses using local adjacency constraints also modeled by fuzzy-shape grammars. Two experiments are conducted on a test database containing a handwritten cursive text 600 characters in length written by ten different writers. First, a reading experiment with ten human readers yields an average character recognition rate of 96.0%. Second, a test of the recognition system gives an average character recognition rate of between 84.4% to 91.6%, depending on whether only the first (best) character sequence output of the system is considered or if the best of the top ten is accepted. This result is achieved without any writer dependent tuning. Moreover, results show that system performances are highly correlated with human performance.  Bibtex:
@inproceedings{Parizeau62, Last modification: 2002/06/14 by parizeau |
|
|
|
 |
|||
|
©2002-. Computer Vision and Systems Laboratory. All rights reserved |
