I'm looking for advice as to the optimal method to recognize a specific set of book covers using Core ML and/or Vision SDK. ie: use camera to detect a book cover jacket and recognize it if one of target covers.
At first I thought that using Vision SDK with an appropriate mlmodel file would be best but I can't find good info for how to create that file. It would fantastic if Apple provided a sample workflow for creating mlmodel files using custom data. Right now it seems to require a degree in AI.