Saliency Detection in Images using Graph-based Rarity, Spatial Compactness and Background Prior
Sudeshna Roy and Sukhendu Das in VISAPP 2014
Introduction
The proposed saliency detection method identifies regions in an image, containing prominent objects, which pop out from the background and helps to focus attention.
- We use rarity of feature based approach based on graph-based spectral rarity and spatial compactness of color, as well as boundary prior constraint using Gaussian mixture model.
- Combination of these two complimentary concepts gives better result in terms of both accuracy and speed.
Algorithm Overview
Downloads
Results
