Search K
Appearance
Appearance
The Google Vision OCR node allows you to perform Optical Character Recognition (OCR) on an image file using the Google Cloud Vision API. This task extracts text from a local image file and stores the result in a variable for use in subsequent workflow steps.
Task
GoogleVisionOCR
The following inputs must be provided by the user in the node configuration modal:
Label | InputType | Description |
---|---|---|
Local Full Path | text | Full path to the local image file to be processed with OCR. |
Output Variable Name | text | Name of the variable that will store the recognized text from the image. |
⚠️ Note: Ensure the file path points to a valid image file that exists on the server or accessible file system. Supported formats typically include
.png
,.jpg
, and
You want to extract text from a scanned invoice image to be used in a data extraction or validation task downstream.
Field | Value |
---|---|
Local Full Path | C:\Automation\Input\InvoiceImage.png |
Output Variable Name | ExtractedText |
After execution, the text content of the image is available in the ExtractedText
variable.
Error Message | Meaning |
---|---|
Failed to get service | Google Cloud service account token retrieval failed. |
Failed to get OCR | OCR API call failed to return a valid result. |
Google Failure: [Exception Message] | An unexpected error occurred during the task execution. |
Ensure the file path is valid and accessible and that the Google Cloud service account is correctly configured with access to the Vision API.
This task uses a service account labeled Google Cloud Platform to authenticate with the Google Cloud Vision API.
This node depends on the following service library components:
ImageDetection.ImageOCRDetection()
from MinuteView.Google.RestService.Services
"Completed"
status with "taskSuccess = true"
.