Multi-Scale Saliency using Local Gradient and Global Colour Features

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Downloads (Pure)

Abstract

In this paper, the issue of scale is addressed in the context of salient object detection. To date, many single scale models have been proposed for detecting salient objects within a scene. Scale is a fundamental problem within image processing, and therefore, multiple scale techniques are investigated and evaluated, as well the presentation of a novel multi-scale saliency model. The proposed model is compared with two state-of-the-art multi-scale saliency algorithms and qualitatively evaluated with respect to algorithmic accuracy and efficiency on the publicly available MSRA10K salient object dataset.
Original languageEnglish
Title of host publication2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019)
Place of PublicationBeijing
Pages28-32
Number of pages5
ISBN (Electronic)9781450372299
DOIs
Publication statusPublished - 18 Aug 2019

    Fingerprint

Keywords

  • Multi-Scale Salient Object Detection
  • Hierarchical Saliency
  • Scale
  • Super-pixels
  • Salient Features
  • Multi-scale salient object detection
  • Hierarchical saliency
  • Salient features

Cite this

Cooley, C., Coleman, S., Gardiner, B., & Scotney, B. (2019). Multi-Scale Saliency using Local Gradient and Global Colour Features. In 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019) (pp. 28-32). Beijing. https://doi.org/10.1145/3357254.3357285