An Efficient Saliency Detection Model Based on Wavelet Generalized Lifting

Xin Zhong, Frank Shih

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Saliency detection refers to the segmentation of all visually conspicuous objects from various backgrounds. The purpose is to produce an object-mask that overlaps the salient regions annotated by human vision. In this paper, we propose an efficient bottom-up saliency detection model based on wavelet generalized lifting. It requires no kernels with implicit assumptions and prior knowledge. Multiscale wavelet analysis is performed on broadly tuned color feature channels to include a wide range of spatial-frequency information. A nonlinear wavelet filter bank is designed to emphasize the wavelet coefficients, and then a saliency map is obtained through linear combination of the enhanced wavelet coefficients. This full-resolution saliency map uniformly highlights multiple salient objects of different sizes and shapes. An object-mask is constructed by the adaptive thresholding scheme on the saliency maps. Experimental results show that the proposed model outperforms the existing state-of-the-art competitors on two benchmark datasets.

Original languageEnglish (US)
Article number1954006
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume33
Issue number2
DOIs
StatePublished - Feb 1 2019
Externally publishedYes

Fingerprint

Masks
Wavelet analysis
Filter banks
Color

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

@article{f6d3d193694f42c4b056fb6287c9c088,
title = "An Efficient Saliency Detection Model Based on Wavelet Generalized Lifting",
abstract = "Saliency detection refers to the segmentation of all visually conspicuous objects from various backgrounds. The purpose is to produce an object-mask that overlaps the salient regions annotated by human vision. In this paper, we propose an efficient bottom-up saliency detection model based on wavelet generalized lifting. It requires no kernels with implicit assumptions and prior knowledge. Multiscale wavelet analysis is performed on broadly tuned color feature channels to include a wide range of spatial-frequency information. A nonlinear wavelet filter bank is designed to emphasize the wavelet coefficients, and then a saliency map is obtained through linear combination of the enhanced wavelet coefficients. This full-resolution saliency map uniformly highlights multiple salient objects of different sizes and shapes. An object-mask is constructed by the adaptive thresholding scheme on the saliency maps. Experimental results show that the proposed model outperforms the existing state-of-the-art competitors on two benchmark datasets.",
author = "Xin Zhong and Frank Shih",
year = "2019",
month = "2",
day = "1",
doi = "https://doi.org/10.1142/S0218001419540065",
language = "English (US)",
volume = "33",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

An Efficient Saliency Detection Model Based on Wavelet Generalized Lifting. / Zhong, Xin; Shih, Frank.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 33, No. 2, 1954006, 01.02.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Efficient Saliency Detection Model Based on Wavelet Generalized Lifting

AU - Zhong, Xin

AU - Shih, Frank

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Saliency detection refers to the segmentation of all visually conspicuous objects from various backgrounds. The purpose is to produce an object-mask that overlaps the salient regions annotated by human vision. In this paper, we propose an efficient bottom-up saliency detection model based on wavelet generalized lifting. It requires no kernels with implicit assumptions and prior knowledge. Multiscale wavelet analysis is performed on broadly tuned color feature channels to include a wide range of spatial-frequency information. A nonlinear wavelet filter bank is designed to emphasize the wavelet coefficients, and then a saliency map is obtained through linear combination of the enhanced wavelet coefficients. This full-resolution saliency map uniformly highlights multiple salient objects of different sizes and shapes. An object-mask is constructed by the adaptive thresholding scheme on the saliency maps. Experimental results show that the proposed model outperforms the existing state-of-the-art competitors on two benchmark datasets.

AB - Saliency detection refers to the segmentation of all visually conspicuous objects from various backgrounds. The purpose is to produce an object-mask that overlaps the salient regions annotated by human vision. In this paper, we propose an efficient bottom-up saliency detection model based on wavelet generalized lifting. It requires no kernels with implicit assumptions and prior knowledge. Multiscale wavelet analysis is performed on broadly tuned color feature channels to include a wide range of spatial-frequency information. A nonlinear wavelet filter bank is designed to emphasize the wavelet coefficients, and then a saliency map is obtained through linear combination of the enhanced wavelet coefficients. This full-resolution saliency map uniformly highlights multiple salient objects of different sizes and shapes. An object-mask is constructed by the adaptive thresholding scheme on the saliency maps. Experimental results show that the proposed model outperforms the existing state-of-the-art competitors on two benchmark datasets.

UR - http://www.scopus.com/inward/record.url?scp=85052965788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052965788&partnerID=8YFLogxK

U2 - https://doi.org/10.1142/S0218001419540065

DO - https://doi.org/10.1142/S0218001419540065

M3 - Article

VL - 33

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 2

M1 - 1954006

ER -