ANALYSIS OF COMPRESSED DOCUMENT IMAGES FOR DOMINANT SKEW MULTIPLE SKEW, AND LOGOTYPE DETECTION

Among the most commonly used compression algorithms for document image s are those defined by the Consultative Committee for International Te lephone and Telegraph (CCITT), CCITT Group III compression is used in all facsimile transmission by modem over analog telephone lines. CCITT Group IV is used in digital transmission and storage of document imag es. Sufficient readily interpretable spatial information exists in the se compressed document images to enable their characterization. In par ticular, it is possible to locate the positions of the bottoms of both black and white structures. Using the bottoms of black structures we can determine the peak strength of their alignment in order to determi ne the dominant skew angle of the image. This method can be expanded, by finding minor peaks, to identify multiple skew angles in single ima ges. The angular distributions of the peak alignments of both white an d black structures are assembled to form an alignment signature. Logot ypes can be designed which generate distinct alignment signatures that are detectable in the compressed representation, (C) 1998 Academic Pr ess.