Tesseract

Tesseract is an open source tool for optical character recognition (OCR) written in C++. It has bindings to many programming languages, including two for Objective-C. You can use it to train your own model or you can use one of the community-trained models (including Ancient Greek, Latin, Hebrew, Farsi, and Polish). The latest version of Tesseract uses the LSTM neural network for character recognition. The library is available under the Apache-2.0 license.

GitHub repository: https://github.com/tesseract-ocr/tesseract