Paper Info
Title
Recognition of Handwritten Numerical Fields in a Large Single-Writer Historical Collection
Abstract
This paper presents a segmentation-based handwriting recognizer and the performance that it achieves on the numerical fields extracted from a large single-writer historical collection. Our recognizer has the particularity that it uses morphing during training: random elastic deformations are applied to fabricate synthetic training character patterns yielding an improved final recognition performance. Two different digit recognizers are evaluated, a multilayer perceptron (MLP) and radial basis function network (RBF), by plugging them into the same left-to-right Viterbi search framework with a tree organization of there cognition lexicon. We also compare with the performance obtained when no dictionary is used to constrain the recognition results.
Year
DOI
Venue
2009
10.1109/ICDAR.2009.8
Barcelona
Keywords
Field
DocType
document handling,handwritten character recognition,multilayer perceptrons,radial basis function networks,Viterbi search framework,elastic deformations,handwritten numerical field recognition,multilayer perceptron,radial basis function network,segmentation-based handwriting recognition,single-writer historical collection,tree organization,Viterbi search,historical document analysis,neural networks,segmentation-based handwriting recognizer,synthetic training data
Morphing,Radial basis function network,Handwriting,Pattern recognition,Segmentation,Computer science,Handwriting recognition,Speech recognition,Multilayer perceptron,Artificial intelligence,Artificial neural network,Viterbi algorithm
Conference
ISSN
ISBN
Citations 
1520-5363 E-ISBN : 978-0-7695-3725-2
978-0-7695-3725-2
7
PageRank 
References 
Authors
0.53
5
4
Name
Order
Citations
PageRank
Marius Bulacu151424.17
Axel Brink2403.15
Tijn van der Zant31229.70
Lambert Schomaker Member4130987.50