Neural network-based systems for handprint OCR applications

Over the last five years or so, neural network (NN)-based approaches have been steadily gaining performance and popularity for a wide range of optical character recognition (OCR) problems, from isolated digit recognition to handprint recognition. We present an NN classification scheme based on an en...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 7(1998), 8 vom: 30., Seite 1097-112
1. Verfasser: Ganis, M D (VerfasserIn)
Weitere Verfasser: Wilson, C L, Blue, J L
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 1998
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM177632771
003 DE-627
005 20231223150625.0
007 cr uuu---uuuuu
008 231223s1998 xx |||||o 00| ||eng c
024 7 |a 10.1109/83.704304  |2 doi 
028 5 2 |a pubmed24n0592.xml 
035 |a (DE-627)NLM177632771 
035 |a (NLM)18276327 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ganis, M D  |e verfasserin  |4 aut 
245 1 0 |a Neural network-based systems for handprint OCR applications 
264 1 |c 1998 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 16.12.2009 
500 |a Date Revised 15.02.2008 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Over the last five years or so, neural network (NN)-based approaches have been steadily gaining performance and popularity for a wide range of optical character recognition (OCR) problems, from isolated digit recognition to handprint recognition. We present an NN classification scheme based on an enhanced multilayer perceptron (MLP) and describe an end-to-end system for form-based handprint OCR applications designed by the National Institute of Standards and Technology (NIST) Visual Image Processing Group. The enhancements to the MLP are based on (i) neuron activations functions that reduce the occurrences of singular Jacobians; (ii) successive regularization to constrain the volume of the weight space; and (iii) Boltzmann pruning to constrain the dimension of the weight space. Performance characterization studies of NN systems evaluated at the first OCR systems conference and the NIST form-based handprint recognition system are also summarized 
650 4 |a Journal Article 
700 1 |a Wilson, C L  |e verfasserin  |4 aut 
700 1 |a Blue, J L  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 7(1998), 8 vom: 30., Seite 1097-112  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:7  |g year:1998  |g number:8  |g day:30  |g pages:1097-112 
856 4 0 |u http://dx.doi.org/10.1109/83.704304  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 7  |j 1998  |e 8  |b 30  |h 1097-112