caa a22 4500 469051493 CHVBK 20180323132831.0 cr unu---uuuuu 170328e19920601xx s 000 0 eng 10.1007/BF02626995 doi (NATIONALLICENCE)springer-10.1007/BF02626995 A computational model for recognition of multifont word images [Elektronische Daten] [Tin Ho, Jonathan Hull, Sargur Srihari] A computational model for the recognition of multifont machine-printed word images of highly variable quality is given. The model integrates three word-recognition algorithms, each of which utilizes a different form of shape and context information. The approaches are character-recognition-based, segmentation-based, and word-shape-analysis based. The model overcomes limitations of previous solutions that focus on isolated characters. In an experiment using a lexicon of 33,850 words and a test set of 1,671 highly variable word images, the algorithm achieved a correct rate of 89% at the top choice and 95% in the top ten choices. Springer-Verlag New York Inc., 1992 character recognition nationallicence word recognition nationallicence pattern recognition nationallicence multiple classifiers nationallicence decision combination nationallicence Ho Tin Center for Document Analysis and Recognition, State University of New York at Buffalo, 226 Bell Hall, 14260, Buffalo, NY, USA aut Hull Jonathan Center for Document Analysis and Recognition, State University of New York at Buffalo, 226 Bell Hall, 14260, Buffalo, NY, USA aut Srihari Sargur Center for Document Analysis and Recognition, State University of New York at Buffalo, 226 Bell Hall, 14260, Buffalo, NY, USA aut Machine Vision and Applications Springer-Verlag 5/3(1992-06-01), 157-168 0932-8092 5:3<157 1992 5 138 https://doi.org/10.1007/BF02626995 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF02626995 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Ho Tin Center for Document Analysis and Recognition, State University of New York at Buffalo, 226 Bell Hall, 14260, Buffalo, NY, USA aut NATIONALLICENCE 700 1- Hull Jonathan Center for Document Analysis and Recognition, State University of New York at Buffalo, 226 Bell Hall, 14260, Buffalo, NY, USA aut NATIONALLICENCE 700 1- Srihari Sargur Center for Document Analysis and Recognition, State University of New York at Buffalo, 226 Bell Hall, 14260, Buffalo, NY, USA aut NATIONALLICENCE 773 0- Machine Vision and Applications Springer-Verlag 5/3(1992-06-01), 157-168 0932-8092 5:3<157 1992 5 138 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer