BLOCKS Reference

Block Reference

Machine Learning

Vision API

This BLOCK uses the Google Cloud Vision API to analyze images stored in Google Cloud Storage (GCS). Results of this analysis are stored into the “Results storage variable” designated within the BLOCK’s properties.

Note for Self-Service Plan users:
The Google Cloud Vision API must be enabled to use this BLOCK. For details, refer to Basic Guide > Hints > Enabling Google APIs

For a detailed example of using the Vision API BLOCK, refer to Using the Google Cloud Vision API Machine Learning service

Property name Explanation
BLOCK name Designate a name for the BLOCK. The name will be displayed on the BLOCK.
GCP service account Select the GCP service account to use with the BLOCK.

Designate the GCS URL which stores the image to be analyzed.

For information regarding optimal image size, resolution, etc., refer to Image file recommendations for the Vision API BLOCK

Information to detect Specify which features the API will analyze the image for. Features which can be analyzed for are as follows:
  • Facial recognition
  • Landmark recognition
  • Logo recognition
  • Object recognition
  • OCR (Text)
  • Dangerous content recognition
  • Color analysis
BLOCK memos Make any comments regarding the BLOCK.
Results storage variable

Designate the variable which will store information detected in the image. Only information related to the features designated within the “Information to detect” property will be stored.

For more details, refer to Output specifications > Vision API

Languages to detect

Select the languages to be analyzed by OCR (text).

  • Multiple languages can be selected.
  • When known, selecting the languages of text in the image may lead to more accurate results.
  • If left blank, languages will be automatically detected.
  • Does not need to be set for languages that use a Latin-based alphabet (such as English).