Frequency-tuned salient region detection

TLDR

Detection of visually salient image regions is useful for applications such as object segmentation, adaptive compression, and object recognition. The authors propose a method that produces full‑resolution saliency maps with well‑defined boundaries of salient objects. The approach exploits color and luminance features, is simple to implement and computationally efficient, and is evaluated against five state‑of‑the‑art methods using frequency‑domain analysis, ground‑truth comparison, and a salient‑object segmentation application. By retaining substantially more frequency content than other techniques, the method preserves object boundaries and outperforms the five algorithms on both ground‑truth evaluation and segmentation, achieving higher precision and better recall.

Abstract

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. These boundaries are preserved by retaining substantially more frequency content from the original image than other existing techniques. Our method exploits features of color and luminance, is simple to implement, and is computationally efficient. We compare our algorithm to five state-of-the-art salient region detection methods with a frequency domain analysis, ground truth, and a salient object segmentation application. Our method outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.