An Investigation of Gradient as a Feature Cue for Saliency Detection

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

11 Downloads (Pure)

Abstract

Salient object detection is a prominent research topic, based on a human’s ability to selectively process conspicuous objects/regions within a scene. With many low-level features being adopted into saliency models, gradient is often overlooked. We investigate the effectiveness of gradient as a feature, applying and evaluating multiple image gradient operators. Scale is also addressed via the use of different sizes of convolutional masks and by varying the neighbour region to calculate gradient contrast. Finally, we present and evaluate a single scale saliency model with the respective gradient cue from each operator, for the detection of salient objects. Each model is evaluated on the publicly available MSRA10K salient object dataset.
Original languageEnglish
Title of host publicationProceedings - 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019)
Place of PublicationBeijing
Pages13-17
Number of pages5
ISBN (Electronic)978-1-4503-7229-9
DOIs
Publication statusPublished - 18 Aug 2019
Event2019 2nd International Conference on Artificial Intelligence and Pattern Recognition - North China University of Technology (NCUT), Beijing, China
Duration: 16 Aug 201918 Oct 2019
http://www.aipr.net

Conference

Conference2019 2nd International Conference on Artificial Intelligence and Pattern Recognition
Abbreviated titleAIPR 2019
CountryChina
CityBeijing
Period16/08/1918/10/19
Internet address

    Fingerprint

Keywords

  • Saliency Detection
  • Gradient Operators
  • Gradient Feature
  • Gradient operators
  • Gradient feature
  • Saliency detection

Cite this

Cooley, C., Coleman, S., Gardiner, B., & Scotney, B. (2019). An Investigation of Gradient as a Feature Cue for Saliency Detection. In Proceedings - 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019) (pp. 13-17). Beijing. https://doi.org/10.1145/3357254.3357281