0

I am trying to solve Baby detection with unet segmentation model. I already collected baby images, baby segments and also passed the adult images as negative (created black segments for this).

So if I will do in this way is unet model can differentiate the adults and babies? if not what I have to do next?

Nick ODell
  • 15,465
  • 3
  • 32
  • 66
  • It really depends on how have you created the segmentation masks. Could you kindly provide more details on your dataset? If you just want to classify an image of a baby or an adult then you can also use an image classifier instead. You do not need to do image segmentation for it. But if you want to do image segmentation, I will request you to go through the Tensorflow tutorial first - https://www.tensorflow.org/tutorials/images/segmentation – pratsbhatt Jul 04 '20 at 12:14
  • Yeah thank you for response. I created the segments with label me tool. I am getting the babies results but model predicting false positive results also. So that is problem... To improve results I added more negative data but that not helping me.. – sahil makandar Jul 04 '20 at 19:49

1 Answers1

1

It really depends on your dataset.

During the training, Unet will try to learn specific features in the images, such as baby's shape, body size, color, etc. If your dataset is good enough (e.g. contains lots of babies examples and lots of adults with a separate color and the image dimensions are not that high) then You probably won't have any problems at all.

There is a possibility however, that your model misses some babies or adults in an image. To tackle this issue, There are a couple of things you can do:

  1. Add Data Augmentation techniques during the training (e.g. random crop, padding, brightness, contrast, etc.)
  2. You can make your model stronger by replacing Unet model with a new approach, such as Unet++ or Unet3+. According to Unet3+ paper, it seems that it is able to outperform both Unet & Unet++ in medical image segmentation tasks: https://arxiv.org/ftp/arxiv/papers/2004/2004.08790.pdf

Also, I have found this repository, which contains a clean implementation of Unet3+, which might help you get started: https://github.com/kochlisGit/Unet3-Plus

LazyAnalyst
  • 426
  • 3
  • 16