Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

To resolve issues starting MATLAB on Mac OS X 10.10 (Yosemite) visit: http://www.mathworks.com/matlabcentral/answers/159016

Size and alignment of a digit in an image for neural network training

Asked by Soumyadip on 12 Jun 2013

Hi, I have been working on OCR using the Neural Network toolbox but I have a few fundamental doubts. Suppose I have the following images of digits:--

Since the digits are of different sizes, will it affect the neural network training and simulation? What are the parameters that a neural network uses to recognise images(like size, pixel values, shape, alignment, etc)? Please advise.

0 Comments

Soumyadip

1 Answer

Answer by Greg Heath on 12 Jun 2013
Accepted answer

The input to the net from a single image is just a column vector of numbers of dimension I obtained by feature extraction. The feature extraction of an image of size r x c can be complicated or as simple as columnisation via

input = image(:);

size(input) = [ I 1 ] = [ r*c 1 ]

Hope this helps.

Thank you for formally accepting my answer

Greg

4 Comments

Greg Heath on 13 Jun 2013

It depends on your feature extraction. The net can only learn what you teach it.

If you use the simplest form, i.e., columnisation, it probably will not work unless you train on a range of sizes.

If your feature extraction involves size normalization then it probably will work.

Soumyadip on 13 Jun 2013

Thanks a lot. Can you provide me any resource on this feature extraction and size normalization stuff?

Greg Heath on 14 Jun 2013

No. However, maybe one of the resident image experts will respond.

If there is no response, try making that another posted question.

Greg Heath

Contact us