2
$\begingroup$

Is it possible for unsupervised learning to learn about high-level, class-specific features given only unlabelled images? For example detecting human or animal faces? If so, how?

$\endgroup$
1
  • $\begingroup$ This question has been flagged as too broad. You might want to edit the title to ask only if it's possible or useful, not how to do it. $\endgroup$
    – Ben N
    Aug 4, 2016 at 0:25

1 Answer 1

1
$\begingroup$

I am assuming each image contains a single object.

It is possible, however, it is not as easy as you might think. Firstly, you need extract as many features as possible: original image, LBP, SIFT, moments, contour descriptors to name a few. Than concatenate these features into a single feature vector. After this step, use clustering. You will need a lot of samples to compensate for the number of features. After clustering, use a correlation method to find which features are related to each cluster.

If you need features to classify within a cluster, you could do a second clustering with full set of features and apply the same method. The features that are selected for a cluster will not be suitable to classify within the cluster.

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .