# Google Vision - Read text from image action

The Read text from image action allows you to read text from an image. Supported images include:

  • Photos: For example, a photograph might contain a street or traffic sign. Google Vision returns the extracted string, individual words, and their bounding boxes.

    Abbey Road photo

  • Scanned documents: Google Vision returns the extracted text with page, block, paragraph, word, and break information.

    Scanned document

# Input

Input field Description
Image content Provide a file contents datapill, a string, a public URL, or a Google Cloud Storage URI.
Image type Select an image type. Google Vision optimizes the output according to the image type.

# Output

Output field Description
Text annotations List of all individual words extracted from the image.
Locale Locale of the extracted word.
Text The extracted word.
Bounding poly The position of the word on the image. Includes X and Y coordinates.
Full text annotation The full text extracted from the image.
Pages Includes details on the pages, such as width, height, and paragraph position.
Full text The full text extracted from the image.


Last updated: 3/7/2025, 7:12:07 PM

On this page