The polynomial method augmented by supervised training for hand printed character recognition

Show simple item record

dc.contributor.author Anderson, Peter en_US
dc.contributor.author Gaborski, Roger en_US
dc.date.accessioned 2006-12-18T17:28:40Z en_US
dc.date.available 2006-12-18T17:28:40Z en_US
dc.date.issued 1995-03-21 en_US
dc.identifier.citation Artificial Neural Networks and Genetic Algorithm (1993) 417-422 en_US
dc.identifier.uri http://hdl.handle.net/1850/3092 en_US
dc.description "The Polynomial method augmented by supervised training for hand-printed character recognition," Presented at The International Conference on Artificial Neural Networks and Genetic Algorithms "ANNGA 93". Held in Innsbruck, Austria, April 1993. en_US
dc.description.abstract We present a pattern recognition algorithm for hand-printed characters, based on a combination of the classical least squares method and a neural-network-type supervised training algorithm. Characters are mapped, nonlinearly, to feature vectors using selected quadratic polynomilas of the given pixels. We use a method for extracting an equidistributed subsample of all possible quadratic features. This method creates pattern classifiers with accuracy competitive to feed-forward systems trained using back propagation; however back propagation training takes longer by a factor of ten to fifty. (This makes our system particularly attractive for experimentation with other forms of feature representation, other character sets, etc.) The resulting classifier runs much faster in use than the back propagation trained systems, because all arithmetic is done using bit and integer operations. en_US
dc.format.extent 180045 bytes en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US en_US
dc.publisher Springer-Verlag en_US
dc.subject Algorithm en_US
dc.subject Neural networks en_US
dc.subject Polynomial method en_US
dc.title The polynomial method augmented by supervised training for hand printed character recognition en_US
dc.type Proceedings en_US

Files in this item

Files Size Format View
PAndersonConfProc03-21-1995.pdf 180.0Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse