General tab
(Distributed) The General tab displays the general properties of the project: the project name, the path to the project files, a project description, a default batch priority, and image display quality. You can also specify the root folder for exporting to files in the Export root path field and configure tool settings. (Standalone) The General tab displays the project name, the path to the project files, and a project description. You can also configure batch type tools. Click the Edit tool button to open the Batch Type Tool Settings dialog box.Stage Tools tab
(Distributed) The Stage Tools tab lists the stage tools you can use in the Advanced schema of the Workflow setup. A stage tool is a stage with a set of scripts and a customizable interface. You can edit base stage tools and create custom tools. For more information, see Stage Tools.Image Processing tab
The Image Processing tab displays the image pre-processing options, which apply to images added manually from a file. (Distributed) You can change these options if required. For more information, see Image pre-processing options.Recognition tab
On the Recognition tab, specify the language of your documents. By default, only the languages for which dictionaries are provided are shown. To see all available languages, select the Show all languages option. Languages marked “ICR” can recognize handwritten and hand-printed text as well as machine-printed text. If the language of your documents is not known in advance, specify several candidate languages, and ABBYY FlexiCapture chooses the right one at the recognition stage.Specifying too many languages may slow down document processing and cause recognition errors.
Advanced recognition settings
- Select one or more Correct page orientation options to rotate a page 180°, 90° clockwise, or 90° counterclockwise when its orientation is detected automatically.
- In the Text type section, specify how a blank form is printed (Typographic, Matrix printer, or Typewriter), and select Use pattern to add a sample pattern.
- Disable barcode extraction – Do not search for barcodes on images. This speeds up recognition considerably.
- Extract 2D barcodes: Data Matrix, Aztec, QR Code – Search for these barcode types. If this option is off, they are not found.
- Extract post barcodes – Search for postal barcodes. If this option is off, they are not found.
Extracting postal barcodes slows down recognition.
- Separated furigana mode – Improve recognition of phonetic tips (furigana) in Japanese.
- Named entity recognition: Extract named entities – Extract information using NLP methods.
Named entity recognition requires an NLP module and a specific license type.
- Extract for all languages – Detect vertically oriented text in any supported language.
- Do not extract – Prevent detection of vertically oriented text.
- Extract for CJK languages – Detect vertical text in Chinese, Japanese, or Korean.
Distortion correction
Click the Advanced button to configure correction of linear and nonlinear image distortions, specify the direction of the scanner’s automatic feeder, and so on.Select Correct linear distortion to specify parameters of image spreading or compression by height and width. Images are scaled by existing anchors (black square, cross, or corner) and by horizontal and vertical separators.
Classification
In the Classification section, specify whether the project uses a classifier or a script.Verification tab
On the Verification tab, select Group fields on Field Verification to group fields in this stage. Fields are grouped by the field or group name specified in the verification properties.Export Destinations tab
On the Export Destinations tab, you can specify, view, or modify export settings for documents that were not recognized. Recognized documents are exported using the export setting specified in the respective Document Definition.Workflow tab
On the Workflow tab, you set up your workflows for thedefault batch type. For more information, see Workflow setup.
