Detect Text in Images Tutorial
.png)
Digitisation has simplified so many things for us in the last few years. For instance, it has made the data from physical documents also available on technological devices. However, it has presented some limitations, like not being able to recognise and extract information from certain formats (scans or images). Luckily, ever since OCR technology was developed, this whole panorama has changed. We have a feature that is perfect for this kind of situation. In this blog, we would like to present the Detect Text in an Image endpoint that can extract body text from images and scans.
Not a fan of reading? No problem! Check out our quick, easy-to-follow video tutorial to learn everything you need!
The first step is to upload the desired document into one of these software programs. Then, we sign up or log into one automation platform where this feature is available (Make, Zapier, and n8n).
After that, we can set up the first Dropbox module and choose the event called "Watch Files", which will look at a specified folder, and it'll trigger whenever a file is uploaded. Later, we need to add a second Dropbox/Google Drive module with the event "Download File" for the 0CodeKit to access this document.
Once the Dropbox module has been set up, we must integrate the 0CodeKit app and find the event "Create temporary URL to file" for 0CodeKit to be able to access the document via the URL. Here, we only have to click on the option "Dropbox/Google Drive - Download a File".
Now, we must integrate the last module. We will add another 0CodeKit module with the event "Detect Text in a Picture with OCR" that will extract all text bodies found in an image. Here, we only need to enter the item "Temporary File URL" into the Image URL field and click on "Save". We choose Finally, we can execute the scenario, and we will receive a list of all the text found as an output.
