OCR Settings

When creating a profile, you can specify if imported documents should be OCRed. You can also configure Import Agent to use a specific OCR language, to decolumnize text, and to temporarily rotate images.

To edit OCR settings

1. Open the Import Agent Configuration Utility.
2. Select Profile from the menu, and then select Options.
3. Select the General tab.
4. Under Laserfiche Distributed Computing Cluster, select the Enable checkbox if you want to connect the Import Agent service to a Laserfiche Distributed Computing Cluster (DCC) installation. When enabled, Import Agent will send OCR requests to the specified DCC Scheduler instead of processing OCR on the Import Engine Computer. Enabling a Distributed Computing Cluster can improve the speed at which OCR is performed.
• Scheduler: Specify the name of the computer where the Laserfiche Distributed Computing Cluster Scheduler is installed.
• Port: Specify the port to use when communicating with the Distributed Computing Cluster Scheduler. By default, DCC uses port 8108.
5. Under OCR, select or clear the following options.
• Language: Select a language to help optimize the character recognition.
• Decolumnize text: Select this option to convert multiple columns of generated text into a single column. Clearing the checkbox will preserve column formatting in the OCRed text, even if that separates words and sentences.
• Perform image enhancement: Images will be temporarily enhanced prior to OCR processing to optimize the processing. Click Configure open the Image Clean-up Options dialog box and configure the desired temporary image enhancements.
• Deskew image: Straighten crooked images.
• Despeckle image: Remove undesired noise from an image.
• Specify the maximum size of noise to be removed (in pixels): Size is specified as both width and height. For example, setting this option to 2 will remove all noise that is equal to or smaller than a 2 pixel x 2 pixel square.
• Rotate image: Rotates images to an orientation that is appropriate for OCR processing. After the OCR process is performed, the image will return to its original orientation.
• Automatically: The direction in which text flows on the page will be detected. The image will be rotated so the text flows horizontally (left to right).
• By this amount: The amount by which the image will be rotated. An image can be rotated by 90, 180, or 270 degrees.
• Line removal: Remove lines from an image.
• Horizontal: Removes horizontal lines from the image. Characters that are damaged due to the line removal will be repaired.
• Vertical: Removes vertical lines from the image. Characters that are damaged due to the line removal will be repaired.
• Optimization priority: Choose one of the following:
• Speed: Reduces the amount of time it takes to OCR. Generated text may be less accurate. Best for documents with clear text.
• Balance: Strikes a balance between speed and accuracy. Best for documents with average text.
• Accuracy: Increases OCR quality. Processing time will also be increased. Best for documents with less clear text.

Note: These settings apply to all profiles.