Learning to Detect a Salient Object

TLDR

The paper investigates salient object detection in images by framing it as a binary labeling problem that separates the salient object from the background. It introduces multiscale contrast, center‑surround histogram, and color spatial distribution features, combines them with a conditional random field, and extends the model to sequential images using dynamic salient features. Experiments on a large, user‑labeled image database and a video segment set demonstrate the effectiveness of the proposed method.

Abstract

In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, to describe a salient object locally, regionally, and globally. A conditional random field is learned to effectively combine these features for salient object detection. Further, we extend the proposed approach to detect a salient object from sequential images by introducing the dynamic salient features. We collected a large image database containing tens of thousands of carefully labeled images by multiple users and a video segment database, and conducted a set of experiments over them to demonstrate the effectiveness of the proposed approach.