I am doing a project to recognize a kind of leaf using ANNs with Emgu CV in C#. My project is to get frames from camera then present them to the ANN and have the ANN tell me if that frame contain a leaf or does not contain a leaf.

I am using 1000 images of leaves that I want to recognize, so if the frame contain a leaf, the ANN will tell me that frame contains one. I do not know what kind of images I should use for the second class. I want to use images perhaps, for example, like pens, rocks, or telephones all together in the second class.