OmniWare Pro 12 ScanSoft manual Text does not get recognized properly

Page 91

Chapter 6

Text does not get recognized properly

Try these solutions if any part of the original document is not converted to text properly during OCR:

Look at the original page image and ensure that all text areas are enclosed by text zones. If an area is not enclosed by a zone, it is generally ignored during OCR. See the section on creating and modifying zones, “Working with zones” on page 57.

Make sure text zones are identified correctly. Reidentify zone types and contents, if necessary, and perform OCR on the document again. See “Zone types and properties” on page 55.

Be sure you do not have an unsuitable template loaded by mistake. If zone borders cut through text, recognition is impaired.

Adjust the brightness and contrast sliders in the Scanner panel of the Options dialog box. You may need to experiment with different settings combinations to get the desired results.

Check the resolution of the original image. Hover the cursor over a page thumbnail for a popup display. If the resolution is significantly above or below 300 dpi, recognition is likely to suffer.

Make sure the correct document languages are selected in the OCR panel of the Options dialog box. Only languages included in the document should be selected.

Turn IntelliTrain on and make some proofing corrections. This is most likely to help with stylized fonts or uniformly degraded documents. If IntelliTrain was running, try turning it off – on some types of degraded documents it may not be able to help.

Do some manual training, or edit existing training to remove unsuccessful training.

If you use True Page as the Text Editor view or for export, recognized text is put into text boxes or frames. Some text may be hidden if a text box is too small. To view the text, place the cursor in the text box and use the arrow keys on your keyboard to scroll to the top, bottom, left, or right of the box.

Check the glass, mirrors, and lenses on your scanner for dust, smudges or scratches. Clean if necessary.

Troubleshooting 91

Image 91
Contents Page G a L N O T I C E S N T E N T S O C E S S I N G D O C U M E N T S O O F I N G a N D E D I T I N G D E Readme File This User’s Guide Online HelpScanning and other information Bold Using this GuideOnline Html Help Getting online HelpContext-Sensitive Help Tech Notes Glossary Installation and setup System requirements Before installing OmniPage Pro Installing OmniPage ProTo install OmniPage Pro Setting up your scanner with OmniPage Pro Setting up your scanner with OmniPage Pro How to start the program Streamlined interface New features in OmniPage ProRegistering your software Dramatic increase in accuracyAdvanced saving options Better proofing and verifyingFormatting levels for display and saving Superior page analysisIntroduction Text formatting What is optical character recognitionOmniPage Pro’s OCR capabilities GraphicsPerform OCR to generate editable text Documents in OmniPage ProBasic processing steps Bring a set of images into OmniPage ProImage Panel OmniPage DesktopToolbars Menu barText Editor Image PanelOmniPage Toolbox Thumbnails Managing documentsDocument Manager Deleting pages from a document Customizing Document Manager columnsPrinting a document OmniPage DocumentsClosing a document How to save to OPD Why save to OPDProcess SettingsScanner Direct OCRCustom Layout ProofingText Editor Processing documents Loading and recognizing sample image files Quick Start GuideScanning and recognizing a single Quick Start Guide Combined Processing overviewAutomatic ManualOther applications Using the OCR WizardAt a later time Automatic processing Stopping and restarting automatic processing Manual processing Start automatically and finish manually Combined processingStart manually and finish automatically Processing with the OCR Wizard Processing from other applications How to use Direct OCR How to set up Direct OCRHow to use OmniPage Pro with PaperPort Processing with Schedule OCR Input from image files Defining the source of page imagesScan color Input from scannerScan black and white Scan grayscaleBrightness and contrast Scanning with an ADFScanning without an ADF Describing the layout of the documentSpreadsheet Single column, no tableMultiple columns, no table Single column with tableAuto-zone a part of a Zones and backgroundsAutomatic zoning Auto-zone a wholeDrawing zones on a process background Manual zoningAuto-zone a page background Drawing zones on an ignore backgroundProcess zone olive Zone types and propertiesGraphic zone green Ignore zone grayText zone brown Table zone blueDraw a single zone Working with zonesMake an irregular zone by addition Make an irregular zone by subtraction Join two zones of the same typeSplit a zone Table grids in the image Remove dividers Insert row dividersInsert column dividers Move dividersHow to save a zone template Using zone templatesHow to modify a zone template How to replace one template with another How to unload a templateHow to delete a template file Proofing and editing Retain Fonts and Paragraphs view Editor display and viewsGreen Non-dictionary words These were recognized No Formatting viewTrue Page view Proofreading OCR resultsVerifying text Verifying text Editing or deleting a user dictionary User dictionariesStarting a user dictionary Loading or unloading a user dictionaryManual training TrainingIntelliTrain Training files Editing character attributes Text and image editingEditing paragraph attributes Editing in True Paragraph stylesTables HyperlinksOn-the-fly editing To hear text Use these keys Reading text aloudYou also have the following keyboard controls Saving and exporting Saving original images Saving recognition results Saving a document as you work Flowing Page FP Selecting a formatting levelNo Formatting NF Retain Fonts and Paragraphs RFPTrue Page TP Spreadsheet Selecting advanced saving optionsChapter Copying pages to Clipboard To copy pages to the Clipboard Sending pages by mailTo send pages by e-mail Saving and exporting Technical information Solutions to try first TroubleshootingTo test OmniPage Pro in VGA mode Windows NT Testing OmniPage ProIncreasing disk space Increasing memory resourcesText does not get recognized properly System or performance problems during OCR Problems with fax recognitionOdma support Advanced features in Schedule OCRFile types for opening and saving images Supported file typesRFP File types for saving recognition resultsTo uninstall or reinstall OmniPage Pro Uninstalling the softwareD E Index Processing steps, 21 Overview of processing Index