This paper describes a method for restoring decorative character images in headlines of newspapers and magazines. Although headlines contain useful keywords for document retrieval, conventional OCRs cannot always recognize them because the characters are often printed in reverse and with various background textures. We made filters that generate multiple candidate images by changing a small number of simple parameters (namely, by setting a threshold for stroke-width filtering and reversing black and white), so that one of the candidates contains a ``normal" image whose characters are printed in black on a white background. If all the candidate images are recognized and an index is created, the keywords in headlines are expected to be retrieved without manual keyword entry and verification processes. In an experiment that we conducted, about 90% of characters in headline images segmented from newspapers were restored in the sense that one of the restored candidate images contained correct character images.
By: Tomio AMANO
Published in: RT0281 in 2002
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .