WEST VIRGINIA PUBLIC SERVICE COMMISSION
The Public Service Commission uses imaging equipment to obtain an accurate picture of documents filed in a case. Imaging filed documents creates a PDF file that can be very large and can take a very long time to download on slower computers and/or internet connections. The PSC is extracting a computer generated text version from scanned documents using optical character recognition (OCR) software and providing these text documents as a convenience for persons who do not have access to high speed communications. The quality of the text document is dependent on the quality and format of the original documents. The software that attempts to recognize text may not be able to correctly recognize all words and formats in a scanned document. Documents which include handwriting, headings, letterhead, postmarks, numbered lines, formatted lists, footnotes and other deviations from plain computer generated text may have numerous errors, including “best guess” text character and misplaced lines. Some “created text” documents may be very difficult to read because of these errors.