Picture water droplets

Developing mathematical theories of the physical world: Open Access research on fluid dynamics from Strathclyde

Strathprints makes available Open Access scholarly outputs by Strathclyde's Department of Mathematics & Statistics, where continuum mechanics and industrial mathematics is a specialism. Such research seeks to understand fluid dynamics, among many other related areas such as liquid crystals and droplet evaporation.

The Department of Mathematics & Statistics also demonstrates expertise in population modelling & epidemiology, stochastic analysis, applied analysis and scientific computing. Access world leading mathematical and statistical Open Access research!

Explore all Strathclyde Open Access research...

Background prior-based salient object detection via deep reconstruction residual

Han, Junwei and Zhang, Dingwen and Hu, Xintao and Guo, Lei and Ren, Jinchang and Wu, Feng (2015) Background prior-based salient object detection via deep reconstruction residual. IEEE Transactions on Circuits and Systems for Video Technology, 25 (8). pp. 1309-1321. ISSN 1051-8215

[img]
Preview
Text (Han-etal-IEEE-TOCASFVT-2015-Background-prior-based-salient-object-detection-via-deep)
Han_etal_IEEE_TOCASFVT_2015_Background_prior_based_salient_object_detection_via_deep.pdf
Accepted Author Manuscript

Download (10MB) | Preview

Abstract

Detection of salient objects from images is gaining increasing research interest in recent years as it can substantially facilitate a wide range of content-based multimedia applications. Based on the assumption that foreground salient regions are distinctive within a certain context, most conventional approaches rely on a number of hand designed features and their distinctiveness measured using local or global contrast. Although these approaches have shown effective in dealing with simple images, their limited capability may cause difficulties when dealing with more complicated images. This paper proposes a novel framework for saliency detection by first modeling the background and then separating salient objects from the background. We develop stacked denoising autoencoders with deep learning architectures to model the background where latent patterns are explored and more powerful representations of data are learnt in an unsupervised and bottom up manner. Afterwards, we formulate the separation of salient objects from the background as a problem of measuring reconstruction residuals of deep autoencoders. Comprehensive evaluations on three benchmark datasets and comparisons with 9 state-of-the-art algorithms demonstrate the superiority of the proposed work.