Text Detection Activity

Overview

The Text Detection activity identifies and extracts words from image files using optical character recognition (OCR) technology. It processes the image content and returns the results in a structured JSON format, including the full extracted string, individual words, and their corresponding bounding boxes.

Parameter Table

Field	Description	Requirement
Api key	Google Cloud Vision API Key	Required
Image path/url	Google Cloud Storage URL of the image	Required
Base64	Base64 encoded string of the image file	Required
Response variable name	Variable name to store the HTTP response	Required

Action Types & Examples

Detected Text

Format: string
Example Result: "This is a sample text detected from the image."

Word-Level Details

Format: array of objects
Example Result: [{"word": "This", "boundingBox": {"x": 10, "y": 20, "width": 30, "height": 10}}, {"word": "is", "boundingBox": {"x": 45, "y": 20, "width": 15, "height": 10}}]

Implementation Examples

Field Setup - Api key: bb3c53c6-8515-4e34-97c8-8281de60972d - Image path/url: gs://cloud-samples-data/vision/ocr/sampleimage.jpg - Base64: /9j/4AAQSkZJRgABAQEAYABgAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/2wBDAQMEBAUEBQkFBQkUDQsNFBQUF……………./58x/8BX+R/9k= - Response variable name: getResponse

Technical Notes

The Text Detection activity leverages Google Cloud Vision API for its OCR capabilities. For successful execution, you must provide either the Image path/url or the Base64 field; providing both is not necessary, but at least one is required. For more detailed information and documentation regarding Google Cloud Vision text detection features, refer to the official Google Cloud Vision documentation.