Classification using ANN

Question

Hi wlel I am doing a project to recognize a pen using ANN with emgucv C# visual studio 2010. I have a question about ANN. I must train ANN in order to recognize a pen. So I have one neuron in ouput layer for two classification(a pen or not pen) So I train ANN with 1100 image of pens and my question is: Do I need to train ANN with any images that is not a pen for the second class(first class is a pen) or If I show a image that ANN was not trained, ANN will assume that is not a pen?

Answer 1

as @Beaker points out, it will assume everything is a pen. However, you can use the level of the output to predict how likely it is to be a pen. But what you really want to do is to train it on pens and non-pens. You may also see better performance with 2 outputs nodes, one for pen and one for not pen. That is typically how people do NN classification, although using a single should work. Be aware that your choice of activation function will guide the range of inputs and outputs between nodes (sigmoid expects 0-1, tanh -1 to 1). Also, the number of levels of the network and the number of neurons in each hidden layer can make a big difference. Make sure you have at least one hidden layer. It is unlikely to do well if you have an input and output layer only.

I would use some online images of random objects to train the negative cases, if you have none. However, as you seem to have a usage of this in mind, giving it images close to the ones it will see when used after training will result in better performance.