Nuance OCR Plugin


Overview

The Nuance HOCR plugin is the part of page processing module of Ephesoft Linux application by default. This plugin uses Nuance OCR tool for generating HOCR XML files. It reads the image files listed in the batch xml of a batch instance and generates HOCR XML file for each one of them.

** Nuance Plugin does not support barcode recognition. 

Description

  1. Nuance OCR Plugin is executed in the page processing phase of the application when all the import processing on the batch has been done.
  2. This plugin extracts the contents of the image using Nuance tool. This tool performs OCR’ing on tiff files.
  3. This plugin uses ”’SETTING.STS”’ file present inside “{”’SharedFolder-intall-dir}\BC??\*” directory”’. In case if no setting file is present in the mentioned folder then the plugin uses its default settings for OCR’ing process and generates the SETTING.STS file inside “{SharedFolder-intall-dir}\BC*” directory.

Configuration

Configurable Properties

Following is the list of configurable properties for the plugin:

Untitled26

Configurable property Type of Value Value Options Description
Nuance Auto Rotate/Deskew switch List of Values *On
*Off
This property is used to auto rotate and de-skew the input images on the basis of orientation and skew angle computed by Nuance.

Nuance Switch List of values *On
*Off This switch is used to turn this plugin ON/OFF. [/table_content][/table_wrap]

Nuance Valid Extensions List of values *Tif Following are the valid image types that can be OCR’ed using Nuance. [/table_content][/table_wrap]

Dependency

This plugin requires an image as an input (with TIFF format). The thumbnails and display images are created using the TIFF processed by Nuance. Hence the plugins ‘Create Display Image Plugin’/ ‘Create Thumbnails Plugin’ must be placed after this plugin.

Untitled25

Dependency on Shared Folders

The batch class folder inside the main shared folder contains a file by the name SETTING.STS. This file is used by the Nuance OCR engine for configuring some of its properties. If the file does not exist in the folder then Nuance uses its default settings for recognizing the image’s data and creates the setting file inside the Batch Class folder with default settings.




Was this article helpful to you?

J.D. Abbey

Comments are closed.