Communications of the ACM
Combining labeled and unlabeled data with co-training
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unlabeled Data Can Degrade Classification Performance of Generative Classifiers
Proceedings of the Fifteenth International Florida Artificial Intelligence Research Society Conference
Exploitation of Unlabeled Sequences in Hidden Markov Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
ICML '06 Proceedings of the 23rd international conference on Machine learning
Semisupervised Learning of Hidden Markov Models via a Homotopy Method
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Novel Connectionist System for Unconstrained Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Self-training Strategies for Handwriting Word Recognition
ICDM '09 Proceedings of the 9th Industrial Conference on Advances in Data Mining. Applications and Theoretical Aspects
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Semi-supervised Learning for Handwriting Recognition
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Language Model Integration for the Recognition of Handwritten Medieval Documents
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Automatic Transcription of Handwritten Medieval Documents
VSMM '09 Proceedings of the 2009 15th International Conference on Virtual Systems and Multimedia
HMM-based Word Spotting in Handwritten Documents Using Subword Models
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Self-training for handwritten text line recognition
CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Multimodal Interactive Pattern Recognition and Applications
Multimodal Interactive Pattern Recognition and Applications
Co-training for Handwritten Word Recognition
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
A Novel Word Spotting Method Based on Recurrent Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence
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
Probability of error of some adaptive pattern-recognition machines
IEEE Transactions on Information Theory
Learning to recognize patterns without a teacher
IEEE Transactions on Information Theory
Learning with a probabilistic teacher
IEEE Transactions on Information Theory
Semi-supervised Learning for Cursive Handwriting Recognition Using Keyword Spotting
ICFHR '12 Proceedings of the 2012 International Conference on Frontiers in Handwriting Recognition
| Hi-index | 0.01 |
The automatic transcription of unconstrained continuous handwritten text requires well trained recognition systems. The semi-supervised paradigm introduces the concept of not only using labeled data but also unlabeled data in the learning process. Unlabeled data can be gathered at little or not cost. Hence it has the potential to reduce the need for labeling training data, a tedious and costly process. Given a weak initial recognizer trained on labeled data, self-training can be used to recognize unlabeled data and add words that were recognized with high confidence to the training set for re-training. This process is not trivial and requires great care as far as selecting the elements that are to be added to the training set is concerned. In this paper, we propose to use a bidirectional long short-term memory neural network handwritten recognition system for keyword spotting in order to select new elements. A set of experiments shows the high potential of self-training for bootstrapping handwriting recognition systems, both for modern and historical handwritings, and demonstrate the benefits of using keyword spotting over previously published self-training schemes.