Saliency detection based object proposal
Aymen Azaza, Ali Douik · 2017
Recently, the use of object proposals has been much introduced in the field of salient object segmentation methods. Object proposal methods provide a limited set of proposals per image which can successively be analyzed on their saliency. In this context, we regard saliency map computation as a regression problem and we used object proposals (selective search) to compute the saliency map. Our method based on low-level features combined with a random forest classifier a saliency classifier is trained. In term of F-measue our approach outperform state of the art results on two datasets.