Monte Carlo Sampling based Salient Region Detection

Abstract

In this paper, a simple and e↵ective method is proposed for salient region detection. Based on the observation that salient regions tend to be compact, connected and surrounded, our original idea is to exploit these three kinds of prior knowledge. However, concepts of spatial structure (such as connectivity and surroundedness) only have definite meanings in binary images. Thus, a Monte Carlo Sampling based Saliency model is proposed. Our model has two main advantages over other methods. Firstly, the result of each sampling process is a binary map which can greatly simplify the combination with prior knowledge of spatial structure. Secondly, our method is naturally parallelized because every sampling process is independent with each other, which makes our method very e cient. Experimental results on two datasets show that, compared with eleven state-of-theart methods, our approach has a competitive performance and also runs very fast.

Automatic Photo to Ideophone Manga Matching

“…This requires knowing where to place it so not to disturb the image or occlude the subject. There are several methods to find salient (and inversely non-salient) regions in an image particularly from the multimedia literature [11,20,14]. For this system, we opted to implement a simplified method for non-salient region detection.…”