Salient Object Detection via Fast Iterative Truncated Nuclear Norm Recovery
Salient object detection is a challenging problem in many areas such as image segmentation and object recognition. Many approaches reveal that the background of an image usually lies in a low-dimensional subspace, while the salient regions perform as noises. Conventional methods apply nuclear norm minimization to recover the low-rank background to get the saliency. However, the nuclear norm could not approximate the rank operator properly. In this paper, we propose a novel salient object detection method called Fast Iterative Truncated Nuclear Norm Recovery (FIT) to detect salient objects. Recent proposed Truncated Nuclear Norm is used as a convex relaxation of the rank operator, which consequently guarantees a higher accuracy while reducing time consumption in saliency detection. Series of experiments have been conducted on widely used public database. The results demonstrate the efficiency of our proposed algorithm compared with the state-of-the-art.
KeywordsSalient Object Detection Low-rank Matrix Recovery Truncated Nuclear Norm
Unable to display preview. Download preview PDF.
- 1.Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
- 3.Chen, T., Cheng, M.-M., Tan, P., Shamir, A., Hu, S.-M.: Sketch2photo: internet image montage. ACM Transactions on Graphics (TOG) 28, 124 (2009)Google Scholar
- 4.Cheng, M.-M., Zhang, G.-X., Mitra, N.J., Huang, X., Hu, S.-M.: Global contrast based salient region detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2011)Google Scholar
- 5.Hou, X., Zhang, L.: Saliency detection: A spectral residual approach. In: IEEE Conference on Computer Vision and Pattern Recognition (2007)Google Scholar
- 6.Hu, Y., Zhang, D., Ye, J., Li, X., He, X.: Fast and accurate matrix completion via truncated nuclear norm regularization. IEEE Transactions on Pattern Analysis and Machine Intelligence (2012) (in preprint)Google Scholar
- 10.Lin, Z., Chen, M., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arxiv:1009.5055 (2010)Google Scholar
- 11.Liu, T., Sun, J., Zheng, N.-N., Tang, X., Shum, H.-Y.: Learning to detect a salient object. In: IEEE Conference on Computer Vision and Pattern Recognition (2007)Google Scholar
- 12.Shen, X., Wu, Y.: A unified approach to salient object detection via low rank matrix recovery. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)Google Scholar
- 13.Zhai, Y., Shah, M.: Visual attention detection in video sequences using spatiotemporal cues. In: Proceedings of the 14th Annual ACM International Conference on Multimedia (2006)Google Scholar