A novel connectionist system for unconstrained handwriting recognition.

Full Abstract

Recognizing lines of unconstrained handwritten text is a challenging task. The difficulty of segmenting cursive or overlapping characters, combined with the need to exploit surrounding context, has led to low recognition rates for even the best current recognizers. Most recent progress in the field has been made either through improved preprocessing or through advances in language modeling. Relatively little work has been done on the basic recognition algorithms. Indeed, most systems rely on the same hidden Markov models that have been used for decades in speech and handwriting recognition, despite their well-known shortcomings. This paper proposes an alternative approach based on a novel type of recurrent neural network, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range bidirectional interdependencies. In experiments on two large unconstrained handwriting databases, our approach achieves word recognition accuracies of 79.7 percent on online data and 74.1 percent on offline data, significantly outperforming a state-of-the-art HMM-based system. In addition, we demonstrate the network's robustness to lexicon size, measure the individual influence of its hidden layers, and analyze its use of context. Last, we provide an in-depth discussion of the differences between the network and HMMs, suggesting reasons for the network's superior performance.

Author information

Author/s: Graves, Alex (A); Liwicki, Marcus (M); Fernández, Santiago (S); Bertolami, Roman (R); Bunke, Horst (H); Schmidhuber, Jürgen (J);

Affiliation: Institut für Informatik,Lehreinheit VI Robotics and Embedded Systems, Technische Universität München, Boltzmannstrasse 3, D-85478 Garching be München, Germany. alex.graves(-atsign-)gmail.com

Journal and publication information

Publication Type: Journal Article; Research Support, Non-U.S. Gov't

Journal: IEEE transactions on pattern analysis and machine intelligence (IEEE Trans Pattern Anal Mach Intell), published in United States. (Language: eng)

Reference: 2009-May; vol 31 (issue 5) : pp 855-68

Dates: Created 2009/03/20; Completed 2009/06/10;

PMID: 19299860, status: MEDLINE (last retrieval date: 6/10/2009, IMS Date: 10 Jun 2009 00:00:00)

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article
(including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.

MeSH headings (categories)

This article was linked to the MESH Headings shown below.

Algorithms
Automatic Data Processing - methods
Handwriting
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Information Storage and Retrieval - methods

This article has not been indexed for related articles as yet, however you can still use the live related article search links below.

See 100+ related articles.

See a large map of 100+ related articles.