Salient Region Detection by UFO: Uniqueness, Focusness and Objectness
Authors:
- Peng JiangPJPeng Jiang
- Haibin LingHLHaibin Ling
- Jingyi YuJYJingyi Yu
- Jingliang PengJPJingliang Peng
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1976-1983
Abstract
The goal of saliency detection is to locate important pixels or regions in an image which attract humans' visual attention the most. This is a fundamental task whose output may serve as the basis for further computer vision tasks like segmentation, resizing, tracking and so forth. In this paper we propose a novel salient region detection algorithm by integrating three important visual cues namely uniqueness, focus ness and objectness (UFO). In particular, uniqueness captures the appearance-derived visual contrast, focus ness reflects the fact that salient regions are often photographed in focus, and objectness helps keep completeness of detected salient regions. While uniqueness has been used for saliency detection for long, it is new to integrate focus ness and objectness for this purpose. In fact, focus ness and objectness both provide important saliency information complementary of uniqueness. In our experiments using public benchmark datasets, we show that, even with a simple pixel level combination of the three components, the proposed approach yields significant improvement compared with previously reported methods.Keywords
This publication has 29 references indexed in Scilit:
- Submodular Salient Region Detection2013
- Saliency Detection via Graph-Based Manifold Ranking2013
- Salient Object Detection: A Discriminative Regional Feature Integration Approach2013
- Automatic salient object extraction with contextual cue2011
- Automatic salient object segmentation based on context and shape prior2011
- Context-aware saliency detection2010
- Learning to predict where humans look2009
- Saliency Detection: A Spectral Residual Approach2007
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- A feature-integration theory of attentionCognitive Psychology, 1980