ARTICLE
vincia01b-art/IDIAP
Combining Neural Gas and Learning Vector Quantization for Cursive Character Recognition
Camastra, Francesco
Vinciarelli, Alessandro
EXTERNAL
https://publications.idiap.ch/attachments/reports/2001/rr01-18.pdf
PUBLIC
https://publications.idiap.ch/index.php/publications/showcite/vincia01b
Related documents
Neurocomputing
51
147-159
2003
IDIAP-RR 01-18
This paper presents a cursive character recognizer, a crucial module in any Cursive Script Recognition system based on a segmentation and recognition approach. The character classification is achieved by combining the use of Neural Gas (NG) and Learning Vector Quantization (LVQ). NG is used to verify whether lower and upper case version of a certain letter can be joined in a single class or not. Once this is done for every letter, it is possible to find an optimal number of classes maximizing the accuracy of the LVQ classifier. A database of 58000 characters was used to train and test the models. The performance obtained is among the highest presented in the literature for the recognition of cursive characters.
REPORT
vincia01b/IDIAP
Combining Neural Gas and Learning Vector Quantization for Cursive Character Recognition
Camastra, Francesco
Vinciarelli, Alessandro
EXTERNAL
https://publications.idiap.ch/attachments/reports/2001/rr01-18.pdf
PUBLIC
Idiap-RR-18-2001
2001
IDIAP
This paper presents a cursive character recognizer, a crucial module in any Cursive Script Recognition system based on a segmentation and recognition approach. The character classification is achieved by combining the use of Neural Gas (NG) and Learning Vector Quantization (LVQ). NG is used to verify whether lower and upper case version of a certain letter can be joined in a single class or not. Once this is done for every letter, it is possible to find an optimal number of classes maximizing the accuracy of the LVQ classifier. A database of 58000 characters was used to train and test the models. The performance obtained is among the highest presented in the literature for the recognition of cursive characters.