Title :
High-level verification of handwritten numeral strings
Author :
Oliveira, L.S. ; Sabourin, R. ; Bortolozzi, F. ; Suen, C.Y.
Author_Institution :
Pontificia Univ. Catolica do Parana, Curitiba, Brazil
Abstract :
In this paper we discuss the use of high-level verification on handwritten numeral strings. First of all, we introduce the concept of levels of verification and present the baseline system used to carry out the experiments. Two different strategies were developed: absolute and one-to-one verifiers. A thorough error analysis is also presented in order to identify under which conditions high-level verification is more appropiate. Experimental results are presented on NIST SD19 database
Keywords :
error analysis; handwritten character recognition; pattern classification; NIST SDI 9 database; absolute verifiers; error analysis; handwritten numeral strings; high-level verification; one-to-one verifiers; pattern classification; Computer vision; Costs; Databases; Error analysis; Focusing; Handwriting recognition; Image segmentation; Machine intelligence; NIST; Pattern recognition;
Conference_Titel :
Computer Graphics and Image Processing, 2001 Proceedings of XIV Brazilian Symposium on
Conference_Location :
Florianopolis
Print_ISBN :
0-7695-1330-1
DOI :
10.1109/SIBGRAPI.2001.963035
