Automate Image Labeling & Logging with Google Sheets and AWS Rekognition

What this workflow does

This workflow gets street photos automatically, finds tags for the photos, and writes data in Google Sheets.

This saves time and stops errors in labeling photos.

Who should use this workflow

This is for digital marketers and teams who need many labeled street images fast.

It helps people who want to stop manual searching, tagging, and writing in sheets.

Tools and services used

• Google Custom Search API: Finds street photos online.
• AWS Rekognition: Detects labels from images using AI.
• Google Sheets: Stores image names, URLs, and labels in rows.
• n8n platform: Runs and connects these services in one workflow.

Inputs, processing, and outputs

Inputs

• Street photo search query “street” via Google Custom Search API.
• Photo data including image URLs and titles.

Processing steps

1. Get one street photo by HTTP Request node.
2. Send image to AWS Rekognition node to detect labels like “road” or “car”.
3. Format image info and labels using Set node to prepare data for Google Sheets.
4. Append structured data as a new row in Google Sheets node.

Outputs

• Google Sheet updated with image title, URL, and detected labels.
• An automated record of images ready for team analysis.

Beginner step-by-step: How to use this workflow in n8n

Import the workflow

1. Download the workflow file using the Download button on this page.
2. Open the n8n editor.
3. Click on “Import from File” and upload the downloaded workflow.

Configure credentials

1. Add your Google Custom Search API credentials with your API Key and Search Engine ID in the HTTP Request node.
2. Add AWS credentials in the AWS Rekognition node. Make sure Rekognition permissions are enabled.
3. Add Google Sheets OAuth2 credentials in the Google Sheets node.
4. Update Google Sheets node with your target sheet ID where the data will go.

Test the workflow

1. Run the workflow once in the editor to check it works.
2. Look at the Google Sheet to confirm the new row appears with data.

Activate for production

1. Turn on the workflow in n8n.
2. Optionally add a schedule trigger to run automatically.
3. Monitor daily for errors in execution logs.

For self hosting n8n, see this helpful link self-host n8n.

Customization ideas

• Change the search query “street” in HTTP Request node to get other images.
• Loop the workflow or use batch settings to fetch more images each time.
• Switch AWS Rekognition operation to facial recognition or detect unsafe content.
• Use a Function node to join label names into one comma string before sending to Google Sheets.
• Add database nodes if you want to save images data in a database instead of sheets.

Handling problems and errors

Problem: AWS Rekognition shows no labels.

Cause: Binary image not passed right or AWS permission missing.

Fix: Check HTTP Request node outputs binary data correctly and verify AWS IAM policy.

Problem: Google Sheets node cannot add new rows.

Cause: Expired OAuth token or wrong sheet ID.

Fix: Reauthorize Google Sheets and confirm correct sheet ID.

Summary of results

✓ Saves hours of manual searching, tagging, and data entry.

✓ Reduces labeling mistakes by automating image analysis.

✓ Creates an up-to-date Google Sheet with street image info and AI tags.

→ Makes image data easy to share and analyze for marketing.