IMAGE PROCESSING SYSTEM FOR DOCUMENTARY DATA

摘要

A method for extracting information from a document bearing (a) first indicia detectable in a first scan mode, using light in a first spectral range, but not detectable in a second scan mode, using light outside the first spectral range, and (b) second indicia detectable in either the first scan mode or second scan mode, where the second indicia represent information encoded in one or more forms decodable by automated symbol recognition resources, comprise several steps. One or more areas of interest on the document are defined in which the seco nd indicia may appear, with the definition including information specifying the form of encoding for the second indicia. The document is scanned in the seco nd mode, using a scanner that produces a pixel image of the indicia detected an d the resulting pixel data are stored in a memory device. An area of interest is selected from those defined for the document and the pixel image of that area of interest is processed with an automated symbol recognition resource suitable for the form of encoding specified for the second indicia in the selected area of interest to produce one or more output records incorporating symbol information representative of the second indicia.