Rejection Strategies for Handwritten Word Recognition

Authors:
Alessandro L. Koerich
Affiliations:
Pontifical Catholic University of Paraná
Venue:
IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition
Year:
2004

Citing 0
Cited 7

Recognition and Verification of Unconstrained Handwritten Words

IEEE Transactions on Pattern Analysis and Machine Intelligence
Rejection strategy for Convolutional Neural Network by adaptive topology applied to handwritten digits recognition

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Transliteration of Online Handwritten Phonetic Pitman's Shorthand with the Use of a Bayesian Network

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Rejection strategies for offline handwritten text line recognition

Pattern Recognition Letters
Rejection strategies for offline handwritten text line recognition

Pattern Recognition Letters
Hidden Markov model-based ensemble methods for offline handwritten text line recognition

Pattern Recognition
Language modelling for the needs of OCR of medical texts

ISBMDA'06 Proceedings of the 7th international conference on Biological and Medical Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we investigate different rejection strategies to verify the output of a handwriting recognition system. We evaluate a variety of novel rejection thresholds including global, class-dependent and hypothesis-dependent thresholds to improve the reliability in recognizing unconstrained handwritten words. The rejection thresholds are applied in a post-processing mode to either reject or accept the output of the handwriting recognition system which consists of a list with the N-best word hypotheses. Experimental results show that the best rejection strategy is able to improve the reliability of the handwriting recognition system from about 78% to 94% while rejecting 30% of the word hypotheses.