This Letter presents a computational model for saliency detection in natural images. While existing approaches usually make use of low-level or high-level visual features for establishing the saliency models, our method relies on midlevel visual cues, i.e., the superpixel representation of the image. In the proposed approach, the given image is first partitioned into superpixels. A fully connected superpixel graph is then constructed, and the random walk on the graph is adopted to measure saliency. In addition, a scheme based on multiple segmentations is used for multiscale processing. Our model has the advantage of generating high-resolution saliency maps with well-defined object borders. Experimental results on publicly available datasets demonstrate the proposed model can outperform the compared state-of-the-art saliency models.

© 2012 Optical Society of America

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

Related Journal Articles

• Large-scale failures of f^-α scaling in natural image spectra (JOSAA)
• The Rose model, revisited (JOSAA)
• Prediction of human observer performance by numerical observers: an experimental study (JOSAA)
• Saliency detection using regional histograms (OL)
• Saliency detection by combining spatial and spectral information (OL)

Related Conference Papers

• Recovery of Myosin Filament Positions in Muscle Electron Micrographs
• Monte Carlo Simulation of the Performance of a Fiber-Optic Position Sensor
• Morphological Feature Quantification of Colonic Crypt Pattern Using Microscope Integrated OCT Scanner
• Hybrid Level-Set Segmentation of MRI on Optical Properties
• Multispectral Images Segmentation of Ancient Documents with Lattice Memories