Saliency detection using parallel non-linear integration of color and gradient using covariances

Anwar, Shahzad; Zhao, Qingjie; Manzoor, Muhammad Farhan

doi:10.1109/intech.2014.6927747

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Background and foreground priors are employed to calculate saliency. In [8], scale is utilised by enlarging the patch sizes at which the dissimilarity measure is calculated. A multi-scale super-pixel approach is presented in [9].…”

Section: Related Workmentioning

confidence: 99%

Multi-scale saliency using local gradient and global colour features

Cooley

Coleman

Gardiner

et al. 2019

Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-scale saliency using local gradient and global colour features

Cooley

Coleman

Gardiner

et al. 2019

Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Within this paper, the main investigation is the effectiveness of gradient as a feature cue for saliency. Anwar et al, describe their method of non-linearly integrating colour and gradient [9]. Saliency is computed using average patch dissimilarity and five different patch sizes for scaling.…”

Section: Placeholder For Copyright Noticementioning

confidence: 99%

An investigation of gradient as a feature cue for saliency detection

Cooley

Coleman

Gardiner

et al. 2019

Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

View full text Add to dashboard Cite

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.

show abstract

Saliency detection using parallel non-linear integration of color and gradient using covariances

Cited by 2 publications

References 23 publications

Multi-scale saliency using local gradient and global colour features

Multi-scale saliency using local gradient and global colour features

An investigation of gradient as a feature cue for saliency detection

Contact Info

Product

Resources

About