I've had excellent results with a combination of the basic Microsoft Document Imaging and Scanning App that comes with MS Office, for image acquisition, followed by Abby Finereader for cleanup, postprocessing, OCR and PDFing.
I scan a book in black and white on a flatbed scanner at school, at 300dpi, then dump the resulting file into ABBY, where I split the pages, then let ABBY automatically figure out the layout; then I let ABBY turn it into a PDF, either leaving the original image on top of underlying OCR text (If I want to keep the original pages) or saving as a pure text PDF file. ABBY is pretty amazing at getting the OCR and layout right with hardly any input from me.
The process is kind of boring (I wish I could afford to pay somebody else to do it) but there's nothing like having all your important texts searchable (on laptop) and portable (on iliad). Too bad the Iliad can't search.
|