BLOCKS Reference

Machine Learning

Image analysis

Overview

This BLOCK uses the Google Cloud Vision API to analyze images stored in Google Cloud Storage (GCS). It stores the results into the variable designated in the Variable property.

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

Properties

Property Explanation
BLOCK name Configure the name displayed on this BLOCK.
GCP service account Select the GCP service account to use with this BLOCK.
GCS image URL

Designate the GCS URL of the image file to be analyzed.

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

Information to detect Specify how the image will be analyzed. Selectable analysis types are as follows:
  • Facial detection
  • Landmark detection
  • Logo detection
  • Object detection
  • Adult content detection
  • Color analysis
  • Text
    • Text
    • OCR (document)

    Text detects text in images. OCR (document) does the same, but its results are optimized for high density text and documents. It also detects information for pages, blocks, paragraphs, words, and line breaks.

BLOCK memos Make notes about this BLOCK.
Variable

Designate the variable that will store the results. Only information related to the features designated within the Information to detect property will be stored.

For more details, refer to Output specifications > Image analysis

Languages

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.
  • Languages will be automatically detected if this is left blank.
  • Does not need to be set for languages that use a Latin-based alphabet (such as English).