We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Image salient object detection with refined deep features via convolution neural network.
- Authors
Dandan Zhu; Lei Dai; Xuan Shao; Qiangqiang Zhou; Itti, Laurent; Ye Luo; Jianwei Lu
- Abstract
Recent advances in saliency detection have used deep learning to obtain high-level features to detect salient regions. These advances have demonstrated superior results over previous works that use handcrafted low-level features for saliency detection. We propose a convolutional neural network (CNN) model to learn high-level features for saliency detection. Compared to other methods, our method presents two merits. First, when performing features extraction, apart from the convolution and pooling step in our method, we add restricted Boltzmann machine into the CNN framework to obtain more accurate features in intermediate step. Second, in order to avoid manual annotation data, we add deep belief network classifier at the end of this model to classify salient and nonsalient regions. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our method performs favorably against the state-of-the-art methods.
- Subjects
ARTIFICIAL neural networks; SIGNAL convolution; BOLTZMANN machine; HUMAN behavior models; IMAGE analysis
- Publication
Journal of Electronic Imaging, 2017, Vol 26, Issue 6, p063018-1
- ISSN
1017-9909
- Publication type
Article
- DOI
10.1117/1.JEI.26.6.063018