Extracting specific objects from an image

Question

Given the dataset of the object, I would like to extract that object from an image.

The object is leaf in my case. It is easy in these kind of situation where there is only one big leaf in front of the camera. This can be done using the edge detected version of this picture as suggested in this answer as we are getting somewhat clear edge of what we want as output.

for reference :

But how can I extract all the leaves from an image in which there are a lot of such leaves. for example :

for reference, edge detected version of this image is

Storfer

At first you will have to write some code. – Sketchbook

@KlausD. I am trying to detect disease in plants using the plantVillage data set. Model is running fine with 80% accuracy. But now I want the model to be able to work in real scenarios. Plant Village contains data like this. link Now, to be able to detect disease in real life, I want to extract leaves from the image. – Storfer