Prediction For Image File

AutomatR.Nanonets.Activities.PredictionForImageFile

The "Prediction For Image File" activity in AutomatR is part of the Nanonets OCR activities package, allowing users to perform OCR predictions on an image using the Nanonets OCR model. This activity aids in extracting text and information from images, enhancing automation processes involving optical character recognition.

Properties

Name	Description
Input
Model ID	The ID of the Nanonets OCR model to use for prediction. String variables containing the Nanonets OCR model ID.
Image Path	The file path of the image on which predictions will be made. String variables containing the file path.
Misc
Display Name	Provides a customizable name for the activity displayed in the workflow. The display name enhances clarity and organization within the automation project. String variables containing the desired display name.
Optional
Delay	Specifies the amount of time (in seconds) to wait before executing the "Prediction For Image File" activity. This can be useful for handling synchronization issues. Integer variables containing the delay duration. Ex.: If the amount of time is 1000 milliseconds or 1 sec, i.e., 1.
Output
Response	Outputs the detailed response generated by the Nanonets OCR model based on the provided image. Variables of type ResultPredictionForImageFile[] to store the OCR prediction results.

How to use:

1. Drag and drop the "Prediction For Image File" activity onto the workflow.
2. Configure the properties by specifying the Nanonets OCR model ID and the file path of the image for OCR predictions.
3. Optionally, configure the delay.
4. Execute the workflow to perform OCR predictions on the specified image using the Nanonets OCR model.
5. Access the detailed OCR prediction results from the output variable "Response" for further processing in the workflow.

Example: Consider an example where the "Prediction For Image File" activity is used to predict text from an image file named "document.jpg" using the Nanonets OCR model with the ID "xyz123" and a delay of 2 seconds:

Prediction For Image File:
  Display Name: "OCR Prediction"
  Model ID: "xyz123"
  Image Path: "C:\Images\document.jpg"
  Delay: 2
  Response: ocrPredictionResults

In this example, the activity performs OCR predictions on the image file "document.jpg" using the Nanonets OCR model with the ID "xyz123". The detailed OCR prediction results are stored in the variable "ocrPredictionResults" for further handling in the workflow.