Efficient Salient Region Detection with Soft Image Abstraction

• Published in: 2013 IEEE International Conference on Computer Vision pp. 1529 - 1536
• Main Authors: Ming-Ming Cheng, Warrell, Jonathan, Wen-Yan Lin, Shuai Zheng, Vineet, Vibhav, Crook, Nigel
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.12.2013
• Subjects: Abstracts; Computational efficiency; Computer vision; Conferences; Correlation; Estimation; Graphical models; Histograms; image abstraction; Image color analysis; Image detection; object of interest segmentation; Permissible error; Pixels; Representations; salient object detection; Similarity; Spatial distribution; visual attention; Visualization

Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering...