23 November 2017 Image salient object detection with refined deep features via convolution neural network
Author Affiliations +
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.
© 2017 SPIE and IS&T
Dandan Zhu, Lei Dai, Xuan Shao, Qiangqiang Zhou, Laurent Itti, Ye Luo, Jianwei Lu, "Image salient object detection with refined deep features via convolution neural network," Journal of Electronic Imaging 26(6), 063018 (23 November 2017). https://doi.org/10.1117/1.JEI.26.6.063018 . Submission: Received: 6 April 2017; Accepted: 1 November 2017
Received: 6 April 2017; Accepted: 1 November 2017; Published: 23 November 2017
JOURNAL ARTICLE
11 PAGES


SHARE
Back to Top