How to create a training example from an RGB image in Matlab?

Question

I have RGB face images of size 60x60. They are matrices of size 60x60x3 in Matlab.

I need to apply some algorithms to these data. But first I need to create training examples for the images. Given one image of size 60x60x3 I will need to create a vector of size 1x10800. I am not sure, should I interleave the R, G and B values for the pixels, should I go column by column or row by row?

Thanks

Answer 1

Usually, it does not matter. For instance, SVM classifier or neural network perceptron are invariant to any permutations of the input. If your image is im, just use im(:) to transform it into a column.