Add custom modeling to Image Processing

[jeffpaul]

Is your enhancement related to a problem? Please describe. We currently utilize Azure's Computer Vision for the Image Processing functionality, but you're forced to accept what the general Computer Vision model has learned to get feedback in the form of alt text and tags. A parallel option could be to utilize the Custom Vision service and further train that model to be site-specific. This would seem to provide a more precise set of image processing results unique to a specific site, though a downside could be pricing of Custom Vision compared to Computer Vision.

Describe the solution you'd like

• [ ] setting to enable Custom Vision instead of Computer Vision
• [ ] if user edits tags or alt text for an image, send that data back to Custom Vision to further train the model

Designs n/a

Describe alternatives you've considered Keep ClassifAI as-is with Computer Vision and instead work to add additional functionality instead of more complex functionality as described here.

Additional context n/a