Search code examples
iosswiftxcodearkitcoreml

ARKit image recognition and text display


I need a project for an application on museums, to implement the functionality that when I frame the paintings of my choice, I visualize the text in AR if possible. Do you think it's feasible or do I have to implement something with the Machine Learning too?


Solution

  • Machine Learning requires lots of samples to be able to recognize images (with some space for errors), since paintings are unique ML doesn’t look like a valuable tool. I would use barcodes instead

    visualize the text in AR would be quite easy