Title :
Confidence guided progressive search and fast match techniques for high performance Chinese/English OCR
Author :
Feng, Zhi-Dan ; Huo, Qiang
Author_Institution :
Dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China
Abstract :
In the past several years, we have been developing a high performance OCR engine for machine printed Chinese/English documents. We present two innovative techniques that contribute to the high efficiency in recognition of the mixed Chinese/English text line. They are (1) a progressive search strategy based on character verification, and (2) a tree-based fast match technique with a confidence-guided adaptive stopping mechanism. The efficacy of the proposed techniques is confirmed by experiments in a benchmark test.
Keywords :
document image processing; image matching; image segmentation; optical character recognition; character verification; confidence guided progressive search; confidence-guided adaptive stopping; experiments; fast match techniques; high performance Chinese OCR; high performance English OCR; image segmentation; machine printed documents; progressive search strategy; text recognition; tree-based fast match technique; Benchmark testing; Books; Character recognition; Computer science; Engines; Image segmentation; Information systems; Optical character recognition software; Text recognition; Typesetting;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1047802