I'm curious why I don't see any projects applying new ML techniques to text recognition (OCR) in those "advertisements" popping up recently; is this because:
- too boring/mundane?
- "solved problem"/too easy? (then where are the [open source] solutions? is Tesseract-ocr advanced enough already? what's its status?)
- too hard? (is Tesseract-ocr using the state-of-the-art techniques?)
Core ML is going to be your best bet. Most training is still done server side using frameworks like TensorFlow, Keras, and PyTorch. Once you've trained your model, you can convert it to Core ML with coremltools or export it to Core ML directly if the platform supports it.
Apple has a couple tools, Turi Create and Create ML, to train ML models specifically for mobile use, but their not nearly as fully featured or widely used.
If you're interested specifically in mobile ML, check out https://heartbeat.fritz.ai. We've got a bunch of resources for mobile machine learning. If you're looking for ready-to-use models or tools to manage them in your app, check out Fritz (https://fritz.ai). Disclaimer, I'm a founder at Fritz which sponsors Heartbeat. Happy to answer any questions!
I'm not sure yet whether i want to do the training on mobile, but i want to try both before i decide so thanks for the resources i'll dig into them. One important question is, are there tools to decrease the size of a model so it'd better fit on mobile? Or is that part of the training?
- too boring/mundane?
- "solved problem"/too easy? (then where are the [open source] solutions? is Tesseract-ocr advanced enough already? what's its status?)
- too hard? (is Tesseract-ocr using the state-of-the-art techniques?)