I just got SwiftOCR to work with small sets of text.
which uses the NeuralNet-MNIST model for text recognition.
You can convert VNTextObservation to a string by the following methods:
Using OpenCV + Tesseract OCR
To perform OpenCV OCR text recognition, we need to install Tesseract v4 which includes a highly accurate deep learning-based model for text recognition.
To write a Python script that:
Performs text detection using OpenCV’s EAST text detector, a highly accurate deep learning text detector used to detect text in natural scene images.
Once we have detected the text regions with OpenCV, we’ll then extract each of the text ROIs and pass them into Tesseract, enabling us to build an entire OpenCV OCR pipeline.
Using Google Vision iOS
Google Vision Text Recognition - Android SDK has text detection but also has iOS cocoapod. So you can try this also.
Hope this answer helps.
If you wish to learn a Machine Learning visit, this Machine Learning Course.