Document analysis in gray level and typography extraction using character pattern redundancies
François Lebourgeois, Hubert Emptoz · 1999
The paper describes the processing of magazine or newspaper images which need to be segmented in gray level. The first part proposes an original method to extract the physical layout of gray-level documents. The second part of the paper describes a rough logical structure by analyzing the typography, aiming to extract relevant information about the logical layout by combining information about colors, typography, and the physical structural layout for use by an automatic document indexation system. Character prototypes were automatically extracted by grouping characters which have the same binary patterns. We suggest using this character-grouping method to extract typographical information and recognize different font styles and sizes used in the document.