Pull text out of web images and log it to a spreadsheet

Automatically finds images from a web search, reads any text in them, and saves the results to a spreadsheet.

How the work actually flows

A straight line. Runs once per each image found.

Pattern: Sequence (1) ยท Multiple Instances with a priori Run-Time Knowledge (14)

flowchart TD trig(("search query submitted")):::human s0["search web for images"]:::svc s1[["detect text in each image"]]:::mi s2["clean and format detected text"]:::task s3[("add results to spreadsheet")]:::store trig --> s0 s0 -->|"one per each image found"| s1 s1 --> s2 s2 --> s3 out[/"spreadsheet of images and extracted text"/]:::out pay{{"research dataset built without manual typing"}}:::pay s3 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
A stepAn outside serviceRuns once per itemA personA record or sheetResultPayoff
Build size
Standard

A mid-size build with several tools working together.

Business functions
Image & Media ProcessingSpreadsheet & Database Ops
Connects
AWS RekognitionGoogle Sheets

The problem it solves

Manually searching for images and typing out any text you find in them is slow and repetitive, especially when you need to do it for many search terms. It's a tedious research task that eats up time better spent elsewhere.

Who it fits

Researchers and marketers building a dataset from images found online.

How it works

  1. A web search pulls images matching a chosen query
  2. Each image is analyzed to detect any text it contains
  3. The detected text is cleaned up and formatted
  4. The results are added to a Google Sheet
What you get

A growing dataset built from images across the web

You get a spreadsheet full of text automatically extracted from images you find across the web.

What you get

A spreadsheet of images and the text detected inside them.

What you need

An AWS account with Rekognition access and a Google Sheets account.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Search the web for images and auto-label them in Google Sheets

Finds images from a web search, identifies what's in each one, and logs the labels to a Google Sheet.

Standard

Read invoices from Gmail and log them to Google Sheets automatically

Pulls invoice attachments out of your inbox, reads the details with AI, and records them in a spreadsheet.

Advanced

Track invoices and automatically chase late payments by email

It logs invoices, emails reminders as they age, and alerts your team on Slack when accounts go to collections.

Advanced

Create AI celebrity selfies and transition videos with GPT-4 and Kling

Uses AI to create realistic celebrity selfie images and smooth transition videos from your photo.

Advanced
Back to the AI Playbook