High performance Chinese OCR based on Gabor features, discriminative feature extraction and model training

Authors:
Qiang Huo;Yong Ge;Zhi-Dan Feng
Affiliations:
Dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China;-;-
Venue:
ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 03
Year:
2001

Citing 0
Cited 14

A PDA-Based Sign Translator

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
An Approach to Extracting the Target Text Line from a Document Image Captured by a Pen Scanner

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Improving Chinese/English OCR Performance by Using MCE-based Character-Pair Modeling and Negative Training

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Gabor Feature Extraction for Character Recognition: Comparison with Gradient Feature

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
A Study On the Use of 8-Directional Features For Online Handwritten Chinese Character Recognition

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Building Compact Classifier for Large Character Set Recognition Using Discriminative Feature Extraction

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Online Chinese Character Recognition System with Handwritten Pinyin Input

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Minimum Classification Error Training for Online Handwriting Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time online multimedia content processing: mobile video optical character recognition and speech synthesizer for the visual impaired

Proceedings of the 1st international convention on Rehabilitation engineering & assistive technology: in conjunction with 1st Tan Tock Seng Hospital Neurorehabilitation Meeting
Building compact MQDF classifier for large character set recognition by subspace distribution sharing

Pattern Recognition
Modeling inverse covariance matrices by expansion of tied basis matrices for online handwritten Chinese character recognition

Pattern Recognition
SwiftPost: a vision-based fast postal envelope identification system

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
A new simplified gravitational clustering method for multi-prototype learning based on minimum classification error training

IWICPAS'06 Proceedings of the 2006 Advances in Machine Vision, Image Processing, and Pattern Analysis international conference on Intelligent Computing in Pattern Analysis/Synthesis
A discriminative linear regression approach to adaptation of multi-prototype based classifiers and its applications for Chinese OCR

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

We have developed a Chinese OCR engine for machine printed documents. Currently, our OCR engine can support a vocabulary of 6921 characters which include 6707 simplified Chinese characters in GB2312-80, 12 frequently used GBK Chinese characters, 62 alphanumeric characters, 140 punctuation marks and symbols. The supported font styles include Song, Fang Song, Kat, He, Yuan, LiShu, WeiBei, XingKai, etc. The averaged character recognition accuracy is above 99% for newspaper quality documents with a recognition speed of about 250 characters per second on a Pentium III-450 MHz PC yet only consuming less than 2 MB memory. We describe the key technologies we used to construct the above recognizer. Among them, we highlight three key techniques contributing to the high recognition accuracy, namely the use of Gabor features, the use of discriminative feature extraction, and the use of minimum classification error as a criterion for model training.