1
$\begingroup$

enter image description hereI am working on a project which involves counting the number of diamonds in the provided image. I have a set of images and a VIA annotated .json file which has all the annotations. How do I proceed with this problem.

  1. what approach to start i.e Object detection vs Instance segmentation ?
  2. what models to choose from MaskRCNN,U-Net, etc (Please suggest) ?

Please guide. Thanks

$\endgroup$
0
1
$\begingroup$

I say that go with Object Detection. Because you already have annoted images. And segmentation applied to locate objects and boundaries (lines, curves, etc.) in images. Ref : ][1]. In Recent days EfficientDet Works very well in object detection. And for implementation look here. Best of luck.

$\endgroup$
13

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.