What are the features of an image?

I need to find the features of the given input image and i need to find the matrices present in the image. Then i need to apply neural network to it. How to do it?

Answer 1

[Walter Roberson]

Basically, anything you can compute using the information in the image qualifies as a "feature" of the image. Average brightness? It's a feature. Third moment of the Knight's Tour of the image? It's a feature. MD-5 hash of the four corner pixels? It's a feature.

How many features does an image have? Answer: an infinite number.

How many useful features does an image have? No-one knows, and the number is "unknowable" at this time. Quite possibly infinite.

Which features should you use for your purposes? You need to experiment. I would not advise looking for the "best" set of features, by the way: a better feature set is likely to be found within a few hundred years at most.

[abinaya sangi]

http://www.mathworks.com/matlabcentral/fileexchange/44429-knights-tour. I have taken coding from the above link.could you help me to do reverse of knight's tour of the same program?

Answer 2

[Image Analyst]

You'd have to use image processing. So that answers the first question.

For the second question, I don't use neural networks so I can't answer that question with as much authority, but I guess you'd use the Neural Network Toolbox to create a neural network, and send your image into it.

[Sivakumaran Chandrasekaran]

Thanks Image Analyst !!

Answer 3

[WangKan]

Is that means that we need to extract proper features according to our purpose? Thank you for your time!

[Image Analyst]

Yes.

[Walter Roberson]

Yes. And the features that turn out to be useful for one purpose might not be the same as for another purpose.

In my experience, it is difficult to predict which features will turn out to be most "explanatory" for any particular goal. A number of times it turned out that the best feature was the relative height of two obscure chemical peaks in the Magnetic Resonance Spectrometry readings, reflecting a biological process that had not been previously explored.