The Community for Technology Leaders
2009 IEEE Conference on Computer Vision and Pattern Recognition (2009)
Miami, FL, USA
June 20, 2009 to June 25, 2009
ISBN: 978-1-4244-3992-8
pp: 1597-1604
R. Achanta , Sch. of Comput.&Commun. Sci. (IC), Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
F. Estrada , Sch. of Comput.&Commun. Sci. (IC), Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
S. Susstrunk , Sch. of Comput.&Commun. Sci. (IC), Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
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.
INDEX TERMS
visual saliency, frequency-tuned salient region detection, full resolution saliency map, color, luminance
CITATION

S. Susstrunk, R. Achanta, F. Estrada and S. Hemami, "Frequency-tuned salient region detection," 2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Miami, FL, USA, 2009, pp. 1597-1604.
doi:10.1109/CVPRW.2009.5206596
202 ms
(Ver 3.3 (11022016))