This demo shows how to use Saliency Objectness [1], as well as Saliency Optimization [2], Saliency Filter [3], Geodesic Saliency [4], and Manifold Ranking [5].
Visit our Project Webpage for more details
Code for [1] by Sai Srivatsa R
Code for [2,3,4,5] by Wangjiang Zhu
If you use this code, please cite both [1] and [2].
To run the demo for default images stored in Data\SRC and to perform evaluation run: >>demo.
The saliency maps are stored in Data\Res .
To obtain saliency maps for custom images using our approach and other methods:
- Add the required files to
Data\SRC. - Add the Objectness Proposals generated by BING [6] to
BingBoxes\. - Now run the demo:
>>demo.
To evaluate our approach and other methods:
- add the ground truth images to
Data\GT. - Now run the demo:
>>demo.
[1] Sai Srivatsa R, R Venkatesh Babu. Salient Object Detection via Objectness Measure. In ICIP, 2015.
[2] Wangjiang Zhu, Shuang Liang, Yichen Wei, and Jian Sun. Saliency Optimization from Robust Background Detection. In CVPR, 2014.
[3] F. Perazzi, P. Krahenbuhl, Y. Pritch, and A. Hornung. Saliency filters: Contrast based filtering for salient region detection. In CVPR, 2012.
[4] Y.Wei, F.Wen,W. Zhu, and J. Sun. Geodesic saliency using background priors. In ECCV, 2012.
[5] C. Yang, L. Zhang, H. Lu, X. Ruan, and M.-H. Yang. Saliency detection via graph-based manifold ranking. In CVPR, 2013.
[6] M.M Cheng and Z. Zhang and W. Y. Lin and P. H. S. Torr. Binarized Normed Gradients for Objectness Estimation at 300fps. In CVPR, 2014.