SALIENT OBJECT DETECTION USING NORMALIZED CUT AND GEODESICS
Paper in proceeding, 2015

Normalized graph cut (Ncut) is conventionally used for partitioning a graph based on energy minimization, and is lately used for salient object detection. Observing that Ncut generates eigenvectors containing cluster information, we propose to incorporate eigenvectors of Ncut with the geodesic saliency detection model for obtaining enhanced salient object detection. In addition, appearance cue and intervening contour cue are jointly exploited for computing the graph affinity. The proposed method has been tested and evaluated on four benchmark datasets, and compared with 12 existing methods. Our results have provided strong support to the robustness of the proposed method.

geodesic saliency

Salient object detection

saliency map

normalized cut

Author

Keren Fu

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Chen Gong

Shanghai Jiao Tong University

Irene Yu-Hua Gu

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Jie Yang

Shanghai Jiao Tong University

Pengfei Shi

Shanghai Jiao Tong University

Proceedings - International Conference on Image Processing, ICIP

15224880 (ISSN)

Vol. 2015-December 1100-1104
978-1-4799-8339-1 (ISBN)

Areas of Advance

Information and Communication Technology

Subject Categories

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/ICIP.2015.7350970

ISBN

978-1-4799-8339-1

More information

Latest update

7/11/2024