First International Workshop on Document Image Analysis for Libraries (DIAL'04)
Construction of Handwriting Databases Using Transcript-Based Mapping
Palo Alto, California
January 23-January 24
ISBN: 0-7695-2088-X
A recognition-based system was developed for constructing handwriting databases. The system automatically recognizes the word and the character images in handwritten document images by applying a transcript mapping algorithm. The transcript-mapping process is modeled as an optimization problem involving multiple word-segmentation hypotheses, word recognition and word alignment. The extensive experiments show that a large number of character and word images can be automatically extracted with very high reliability.
Citation:
Bin Zhang, Catalin Tomai, Sargur Srihari, Venu Govindaraju, "Construction of Handwriting Databases Using Transcript-Based Mapping," dial, pp.288, First International Workshop on Document Image Analysis for Libraries (DIAL'04), 2004