Error-Correcting Output Coding for the Convolutional Neural Network for Optical Character Recognition
Authors:
- Huiqun DengHDHuiqun Deng
- George StathopoulosGSGeorge Stathopoulos
- Ching Y. SuenCSChing Y. Suen
- 1 January 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15205363,p. 581-585
Abstract
It is known that convolutional neural networks (CNNs) are efficient for optical character recognition (OCR) and many other visual classification tasks. This paper applies error-correcting output coding (ECOC) to the CNN for segmentation-free OCR such that: 1) the CNN target outputs are designed according to code words of length N; 2) the minimum Hamming distance of the code words is designed to be as large as possible given N. ECOC provides the CNN with the ability to reject or correct output errors to reduce character insertions and substitutions in the recognized text. Also, using code words instead of letter images as the CNN target outputs makes it possible to construct an OCR for a new language without designing the letter images as the target outputs. Experiments on the recognition of English letters, 10 digits, and some special characters show the effectiveness of ECOC in reducing insertions and substitutions.Keywords
This publication has 4 references indexed in Scilit:
- Data-driven decomposition for multi-class classificationPattern Recognition, 2008
- Evaluation of convolutional neural networks for visual recognitionIEEE Transactions on Neural Networks, 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Solving Multiclass Learning Problems via Error-Correcting Output CodesJournal of Artificial Intelligence Research, 1995