Global contrast based salient region detection

TLDR

Reliable estimation of visual saliency is essential for many computer vision tasks such as image segmentation, object recognition, and adaptive compression. The authors propose a regional contrast‑based saliency extraction algorithm. The algorithm evaluates global contrast differences and spatial coherence simultaneously. The algorithm is simple, efficient, produces full‑resolution saliency maps, outperforms existing methods with higher precision and recall, and can generate high‑quality segmentation masks.

Abstract

Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.