I was very excited to see ImageCases
being documented in version 12. But I immediately desired a mechanism for adding more entities to ImageCases
, especially given that we can create our own custom entities now.
Assuming you have many images containing a new object class and you want to detect them and their ImageBoundingBoxes
, is there any undocumented method or 3rd party service to achieve this?
I’m thinking that there might be a way to combine Classify
with the new Image Pyramid functionality and/or ImageCases
’s internal feature network and do some transfer learning.