I am on a project of vehicle type Identification (MUV,jeep,Sedan,etc) from images and Here is what I have done up-to now on
I am working only on the sideview of images.
Input Image : Masked image
Then I detected the corners easily
Now I got a matrix
40 corner coordinates thus I got a matrix of
I converted it to a linear form using
C=C(:); so I got
C=[1x80] (as Neural Network destroys coordinates information itself) for 1 image
But I have about 9 image for each class(MUV,Jeep,Sedan) so I made a matrix using C matrix to form a new matrix say
Now I have a corner feature of
1. What Other features could I use or the corner feature would itself be fine enough.(may be SURF features)
2. The Input Format of NN is
n=number of features and
m=total images and target Format is
c=number of classes (MUV,Sedan,jeep) and 'm=total images'. Am I right here?