Low resolution character recognition by dual eigenspace and synthetic degraded patterns

Authors:
Jun Sun;Yushinobu Hotta;Yutaka Katsuyama;Satoshi Naoi
Affiliations:
Fujitsu R&D Center Co., Ltd., Beijing, P. R. China;Fujitsu Laboratories LTD, Nakahara-ku, Kawasaki, Japan;Fujitsu Laboratories LTD, Nakahara-ku, Kawasaki, Japan;Fujitsu Laboratories LTD, Nakahara-ku, Kawasaki, Japan
Venue:
Proceedings of the 1st ACM workshop on Hardcopy document processing
Year:
2004

Citing 4
Cited 5

Optical character recognition

Optical character recognition
High-Speed, High-Accuracy Binarization Method for Recognizing Text in Images of Low Spatial Resolutions

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Progress in Camera-Based Document Image Analysis

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
A novel face recognition system using hybrid neural and dual eigenspaces methods

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Camera based Degraded Text Recognition Using Grayscale Feature

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Recognition of camera-captured low-quality characters using motion blur information

Pattern Recognition
Sparse representation based on K-nearest neighbor classifier for degraded Chinese character recognition

PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
Robust chinese character recognition by selection of binary-based and grayscale-based classifier

DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
RII: Renovating the irregular illumination of digital image archives

Journal of Visual Communication and Image Representation

Quantified Score

Hi-index	0.00

Visualization

Abstract

As the rapid progress of digital imaging technology, the requirements of character recognition for text embedded in image increase dramatically. Many image text characters are in low resolution with heavy degradation. Traditional OCR methods don't have good recognition performance on these degraded images due to poor binarization. In this paper, a novel feature extraction method based on dual eigenspace and synthetic pattern generation is proposed to recognize character images under low resolution. A subpixel grayscale normalization method is first used to normalize the low resolution character images. The dual eigenspace performs classification from coarse to fine. The multi-templates generated from the synthetic patterns provide good robustness against real degradation. Experimental results indicate that our method is very effective on low resolution Japanese character images.