Parsing N-Best Lists of Handwritten Sentences

Authors:
Matthias Zimmermann;Jean-Cédric Chappelier;Horst Bunke
Affiliations:
-;-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 8
Cited 2

Off-Line, Handwritten Numeral Recognition by Perturbation Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Parsing and Recognition of City, State, and ZIP Codes in Handwritten Addresses

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
A2iA Check Reader: A Family of Bank Check Recognition Systems

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
A Hybrid Large Vocabulary Handwritten Word Recognition System Using Neural Networks with Hidden Markov Models

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Hidden Markov Model Length Optimization for Handwriting Recognition Systems

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Integrated Segmentation and Recognition of Handwritten Numerals: Comparison of Classification Algorithms

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Optimizing the Number of States, Training Iterations and Gaussians in an HMM-based Handwritten Word Recognizer

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Offline Recognition of Large Vocabulary Cursive Handwritten Text

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2

Recognition of Cursive Roman Handwriting - Past, Present and Future

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Offline Grammar-Based Recognition of Handwritten Sentences

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates the application of a probabilistic parser for natural language on the ist of the N-best sentences produced by an off-ine recognition system for cursive handwritten sentences. For the generation of the N-best sentence ist an HMM-based recognizer including a bigram anguage model is used. Theparsing of the sentences is achieved by a bottom-upchart parser for stochastic context-free grammars whichproduces the parse tree of the input sentence as well asthe word tags. From a collection of corpora we extractthe linguistic resources to build the lexicon, a word bigram model and the stochastic context-free grammar.Results from experiments indicate an increase of theword and sentence recognition rate when using the proposed combination scheme.