Fast Convolutional OCR with the Scanning N-Tuple Grid

Authors:
Simon M. Lucas;Kyu Tae Cho
Affiliations:
University of Essex, UK;University of Essex, UK
Venue:
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Year:
2005

Citing 12
Cited 1

Alpha-nets: a recurrent “neural” network architecture with a hidden Markov model interpretation

Speech Communication - Neurospeech
Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques

IEEE Transactions on Pattern Analysis and Machine Intelligence
Improving the Clustering Performance of the Scanning n-Tuple Method by Using Self-Supervised Algorithms to Introduce Subclasses

IEEE Transactions on Pattern Analysis and Machine Intelligence
Document Image Decoding Using Markov Source Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Methods, Report and Survey for the Comparison of Diverse Isolated Character Recognition Results on the UNIPEN Database

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Probability Table Compression for Handwritten Character Recognition

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Fast Lexicon-Based Word Recognition in Noisy Index Card Images

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
ICDAR 2003 Robust Reading Competitions

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
A New Chain-code Quantization Approach Enabling High Performance Handwriting Recognition based on Multi-Classifier Schemes

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Robust Real-Time Face Detection

International Journal of Computer Vision
Sequence Recognition with Scanning N-Tuple Ensembles

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03

Orientational features with the SNT-grid

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a novel high speed convolutional character recognition system. Convolutional mode operation means that no prior localization or segmentation of characters is required, making this mode extremely robust. The method uses a 2-d n-tuple grid to sample the image, but decomposes the address calculations into two onedimensional scans. This simple innovation leads to a very fast system, and speeds in excess of 100,000 recognitions per second have been achieved for a 10-class character recognition problem, when operated in convolutional mode. Quantitative performance results show an error rate of 4.3% on the MNist dataset of isolated hand-written characters. Qualitative results are presented on museum archive card images, indicating that the method has great potential for the character recognition component in a document image analysis system for images of this type.