Hand Written Text Extraction node is used to convert, extract, or remove handwritten text from a document.
It can perform the following operations:
- Convert handwritten text in document to machine-readable text.
- Extract handwritten segment as image.
- Extract only handwritten text as machine-readable text.
- Remove handwritten text from the document.
It takes an input PDF file/fileID and returns a fileID with the necessary operation executed on the file. A Function Node is used in conjunction to download the file from Server to your local machine.
Configuration for Hand Written Text Extraction
- Double-click the Hand Written Text Extraction node.
- Enter the Configuration Name and Clusters in Configurations tab.
- Enter the Project ID, Private key ID, Private key, and Client ID obtained from the Google Cloud Platform account.
To know more about Handwritten Text Extraction Prerequisites, click here.
Properties of Hand Written Text Extraction Node
- Navigate to Properties tab and enter Name and Description.
- Enable Mark run Failure on Node Fail and Mark run Failure on Node Fail options as required.
- Select the Mode from the drop-down. The following Modes are listed.
- Convert Handwritten Text to Print.
- Extract Handwritten Segment as Image.
- Extract only Handwritten Text.
- Remove Handwritten Text.
Result of Execution in Hand Written Text Extraction Node
After executing task, Result of Execution window is displayed with Input, Output, and Run Info tabs.
- Output: The fileID of the document and status of the Task is displayed.
- Input: The input variables that are mapped to the node are displayed.
- Run Info: The Run Details, Configuration Details, and Machine Details are displayed.
- Run Details include Run ID, Sequence Number, Iteration ID, and Total Node Execution Time (in seconds).
- Configuration Details include Configuration Name, Clusters, and Config Level.
- Machine Details include ID, Name, Host, Port, Iteration Start Time, Iteration End Time, Iteration Time (in seconds).