Visual Saliency by Extended Quantum Cuts
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Details
| Original language | English |
|---|---|
| Title of host publication | 2015 IEEE International Conference on Image Processing (ICIP) |
| Publisher | IEEE SIGNAL PROCESSING SOCIETY |
| Pages | 1692-1696 |
| Number of pages | 5 |
| ISBN (Print) | 978-1-4799-8339-1 |
| DOIs | |
| Publication status | Published - 2015 |
| Publication type | A4 Article in a conference publication |
| Event | IEEE International Conference on Image Processing - Duration: 1 Jan 1900 → … |
Conference
| Conference | IEEE International Conference on Image Processing |
|---|---|
| Period | 1/01/00 → … |
Abstract
In this study, we propose an unsupervised, state-of-the-art saliency map generation algorithm which is based on a recently proposed link between quantum mechanics and spectral graph clustering, Quantum Cuts. The proposed algorithm forms a graph among superpixels extracted from
an image and optimizes a criterion related to the image boundary, local contrast and area information. Furthermore, the effects of the graph connectivity, superpixel shape irregularity, superpixel size and how to determine the affinity between superpixels are analyzed in detail. Furthermore, we introduce a novel approach to propose several saliency maps. Resulting saliency maps consistently achieves a state-of-the-art performance in a large number of publicly available benchmark datasets in this domain, containing
around 18k images in total.
an image and optimizes a criterion related to the image boundary, local contrast and area information. Furthermore, the effects of the graph connectivity, superpixel shape irregularity, superpixel size and how to determine the affinity between superpixels are analyzed in detail. Furthermore, we introduce a novel approach to propose several saliency maps. Resulting saliency maps consistently achieves a state-of-the-art performance in a large number of publicly available benchmark datasets in this domain, containing
around 18k images in total.