Salient Object Detection via Fast Iterative Truncated Nuclear Norm Recovery
- Cite this paper as:
- Zou C., Hu Y., Cai D., He X. (2013) Salient Object Detection via Fast Iterative Truncated Nuclear Norm Recovery. In: Sun C., Fang F., Zhou ZH., Yang W., Liu ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg
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.