CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

SALIENT OBJECT DETECTION USING NORMALIZED CUT AND GEODESICS

Keren Fu (Institutionen för signaler och system, Signalbehandling) ; Chen Gong ; Irene Y.H. Gu (Institutionen för signaler och system, Signalbehandling) ; Jie Yang ; Pengfei Shi
IEEE International Conference on Image Processing ICIP, 27-30 Sept., 2015 (1522-4880). p. 1100-1104. (2015)
[Konferensbidrag, refereegranskat]

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.

Nyckelord: Salient object detection, normalized cut, geodesic saliency, saliency map



Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2015-05-29. Senast ändrad 2016-05-27.
CPL Pubid: 217789

 

Läs direkt!


Länk till annan sajt (kan kräva inloggning)


Institutioner (Chalmers)

Institutionen för signaler och system, Signalbehandling

Ämnesområden

Informations- och kommunikationsteknik
Bildanalys

Chalmers infrastruktur