Title :
Text-line extraction and character recognition of document headlines with graphical designs using complementary similarity measure
Author :
Sawaki, Minako ; Hagita, Norihiro
Author_Institution :
NTT Basic Res. Labs., Kanagawa, Japan
fDate :
10/1/1998 12:00:00 AM
Abstract :
A method for recognizing characters on graphical designs is proposed. A new projection feature that separates text-line regions from backgrounds, and adaptive thresholding in displacement matching are introduced. Experimental results for newspaper headlines with graphical designs show a recognition rate of 97.7 percent
Keywords :
adaptive systems; document image processing; feature extraction; image matching; image segmentation; optical character recognition; OCR; adaptive thresholding; character recognition; character segmentation; displacement matching; document headlines; projection feature; similarity measure; text-line extraction; Adaptive optics; Character recognition; Computer Society; Gray-scale; Image segmentation; Natural languages; Optical character recognition software; Optical computing; Optical devices; Pattern matching;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
