Computer Vision, Graphics, and Image Processing
A New Methodology for Gray-Scale Character Segmentation and Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Direct Gray-Scale Extraction of Features for Character Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection of Word Groups Based on Irregular Pyramid
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Hi-index | 0.00 |
Compared to binary images that most text extractionmethods work on, gray scale images provide much moreinformation for the extraction task. On the other handcomplication also arises in determining the subjecttextual content from its background region (ie.thresholding) before the actual text extraction processcan begin. Differing from the usual sequence of processeswhere document images are binarized before the actualtext extraction, this paper proposes a new method by firstsegmenting individual subject areas with the help of anirregular pyramid to be followed by the binarizationprocess. This permits the focus of attention only on theappropriate subject areas for the binarization processbefore text recognition. Our method overcomes thedifficulty in global binarization to find a single value to fitall. It also avoids the common problem in most localthresholding technique of finding a suitable window size.As shown in our experimented result, our methodperformed well in both text segmentation and binarizationby varying the sequence of processing.