Two-stage salient object identification and segmentation based on irregularity

Date

2021-08-16

Advisors

Journal Title

Journal ISSN

ISSN

1380-7501

Volume Title

Publisher

Springer

Type

Article

Peer reviewed

Yes

Abstract

In this paper, we introduce a new approach for saliency identification based on the irregularity of the region both globally and locally. The new technique utilises the local and global features of the surrounding region of the pixels. The object is considered to be salient if it is salient both locally and globally. The local saliency identification (LSI) is used to identify the saliency of the object based on the structure of the object while the global saliency identification deification (GSI) identifies the saliency of the region based on the contrast of the object with respect to the entire background.

Description

The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.

Keywords

Irregularity, Saliency, Image Processing, Thresholding, fuzzy

Citation

Al-Azawi, M., Yang, Y. and Istance, H. (2021) Two-stage salient object identification and segmentation based on irregularity. Multimedia Tools and Applications, 80, pp. 33275–33295.

Rights

Research Institute