Font group identification using reconstructed fonts

Abstract

Ideally, digital versions of scanned documents should be represented in a format that is searchable, compressed, highly readable, and faithful to the original. These goals can theoretically be achieved through OCR and font recognition, re-typesetting the document text with original fonts. However, OCR and font recognition remain hard problems, and many… (More)
DOI: 10.1117/12.873398

3 Figures and Tables

Topics

  • Presentations referencing similar topics