Prediction of photo shareability using supervisedlearning

University essay from KTH/Skolan för datavetenskap och kommunikation (CSC)

Author: Emil Arfvidsson; [2013]

Keywords: ;

Abstract: Many photos are taken every day. Some of them are shared to friends, acquaintances or family. Automatic prediction of what photos are shareable is investigated. The prediction techniques use supervised machine learning, trying to separate shareable images from non-shareable images. High performing prediction is shown to be hard to solve accurately using the chosen approach.

  AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)