I'm working on a project about using Eigenfaces for classification: http://courses.cs.washington.edu/courses/cse455/10wi/projects/p2/ . But in here: http://www.cs.cmu.edu/~pmuthuku/mlsp_page/assignments/assignment2_hints.html it says that the image needs to be converted to grayscale. Is this true? The first link does not say anything about that.

  • $\begingroup$ Do you see colored images in the first link? No. And there is also PCA is a technique by which we reduce the dimensionality of data points. For example, consider the space of all 20-by-30 pixel grayscale images.. Nothing explicit. But interpret for yourself. (Without customized models, color-information is usually not really helping in such a modestly complex framework) $\endgroup$
    – sascha
    Aug 1, 2016 at 20:51
  • $\begingroup$ @sascha Thank you , I have fixed the problem :) :) $\endgroup$ Sep 7, 2016 at 7:29


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.