A novel word spotting algorithm using bidirectional long short-term memory neural networks

Authors:
Volkmar Frinken;Andreas Fischer;Horst Bunke
Affiliations:
Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland;Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland;Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland
Venue:
ANNPR'10 Proceedings of the 4th IAPR TC3 conference on Artificial Neural Networks in Pattern Recognition
Year:
2010

Citing 5
Cited 4

On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

ICML '06 Proceedings of the 23rd international conference on Machine learning
Matching ottoman words: an image retrieval approach to historical document indexing

Proceedings of the 6th ACM international conference on Image and video retrieval
Text search for medieval manuscript images

Pattern Recognition
A Novel Connectionist System for Unconstrained Handwriting Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence

Improving handwritten keyword spotting with self-training

Proceedings of the 2011 ACM Symposium on Applied Computing
Lexicon-free handwritten word spotting using character HMMs

Pattern Recognition Letters
Combining neural networks to improve performance of handwritten keyword spotting

MCS'10 Proceedings of the 9th international conference on Multiple Classifier Systems
Boosting the handwritten word spotting experience by including the user in the loop

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Keyword spotting refers to the process of retrieving all instances of a given key word in a document. In the present paper, a novel keyword spotting system for handwritten documents is described. It is derived from a neural network based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e. it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm. We demonstrate that such a system has the potential for high performance. For example, a precision of 95% at 50% recall is reached for the 4,000 most frequent words on the IAM offline handwriting database.