For my homework I must do a palm recognition with nearest neighbor method. I get features of every palm with SIFT algorithm. But every picture of a palm has different number of features - different dimensions. At first I must do the learning set and training set. Ok I do that.
But how can I found the nearest neighbor from training set in learning set?
example in training]set: a=[1 2 3; 4 5 6 ; 7 8 9]
learning set : b=[1 4 5; 7 4 1; 8 5 4; 2 3 1]
c=[1 1 1; 2 2 2]
How can I found the nearest neighbor for a (b or c)? I must write the code in Matlab so if anyone know any hint how can measure the distance between two matrix which have not the same dimension I will be very grateful.
Thank you in advance.
Unless you know which dimensions match which then I dont see how you can do this?
Imagine trying to find something in 3D space but only knowing the x and y coordinates!