Transact

⌘K
  1. Home
  2. Transact
  3. Features and Functions
  4. Administrator Role and Fe...
  5. Batch Class Management
  6. Document Types
  7. Training Transact for Document Classification

Training Transact for Document Classification

A well-formed set of HOCR xml files which are placed in a hierarchical structure such as: Batch Class > Document type > Page type are used for the purpose of registering few standard HOCR xml documents with Lucene search engine. This process is called learning because it is like feeding the xml files into Lucene’s memory by creating Lucene indexes. HOCR files in batch instance are compared with these memorized indexes to find the best match and classify the pages. Note that document training is a one-time process. Training makes the classification process fast as no index needs to be generated at runtime to classify the documents.

Steps to Train Document Classification

You can train document classification using single or multipage .tif, .tiff, or .pdf documents.

  1. Create the document type.
  2. Select the document that Transact needs to recognize for classification. You can either drag the sample file to the Upload Test Classification File(s) pane, or click the Upload Test Classification File(s) link.

Transact will process and learn the documents.

C:UsersgajendrayadavDesktopScreen shots4.0.0.0_Document_Learning_10001.jpg

Note: If the uploaded document is a single page document, a single page will be copied to Application-Checklist_First_Page. If the uploaded document is multipage, the first and last page of the document will be copied in the Application-Checklist_First_Page and Application-Checklist_Last_Page, respectively, and all other pages of the document will be copied in Application-Checklist_Middle_Page. Suppose the user has created the Application-Checklist document type in batch class BC1 and saved this document type. It creates the necessary folders where tiff files to be learned can be placed. In this case, the folder will be created under [Ephesoft_install_directory]/SharedFolders/[Batch-Class-Id]/lucene/[clasification-method-sample] folder. The following three subfolders will be created in this case:

  • Application-Checklist_First_Page
  • Application-Checklist_Last_Page
  • Application-Checklist_Middle_Page

Learn File(s)

This feature learns the documents present in the folders of document type.

On learning, the following action happens:

1. Hocr files will be created in the folder “Ephesoft-install-dirSharedFoldersBatch-Class-Idlucene-search-clasification-sample” for lucene learning.

2. Thumbnails will be created in the folder “Ephesoft-install-dirSharedFoldersBatch-Class-Id image-classification-sample” for image classification.

3. Indexes will be created in the folder “Ephesoft-install-dirSharedFoldersBatch-Class-Id learn-index” for index learning.

View Learn File(s)

User can navigate using keyboard to see learn files result for different document types.

User can view learned files of a document type on the UI.

Select any document type and click on ‘View Learn File(s)’ button, following UI will be presented:

C:UsersgajendrayadavDesktopScreen shots4.0.0.0_Document_Learning_10002.jpg

The Result page will have the following given columns:

Column Name Type of value Value options Description
File Name String NA It represents the uploaded file name.
Page Type String
  • FIRST
  • LAST
  • MIDDLE
It specifies this file is learned as first, last or middle page.
Image Classification Boolean
  • True
  • False
It specifies whether thumbnail created or not. It’s value will be true If thumbnail created else false.
Lucene Learning Boolean
  • True
  • False
It specifies whether hocr files created or not. It’s value will be true if hocr file created else false.

The Ephesoft software is now ready and has learned the document type of Application-Checklist.