A low-complexity wavelet-based visual saliency model to predict fixations

Manjula Narayanaswamy, Yafan Zhao, Wai Keung Fung, Nazila Fough

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddCyfraniad mewn cynhadleddadolygiad gan gymheiriaid

2 Dyfyniadau (Scopus)

Crynodeb

A low-complexity wavelet-based visual saliency model to predict the regions of human eye fixations in images using low-level features is proposed. Unlike the existing wavelet-based saliency detection models, the proposed model requires only two channels - luminance (Y) and chrominance (Cr) in YCbCr colour space for saliency computation. These two channels are decomposed to their lowest resolution using Discrete Wavelet Transform (DWT) to extract local contrast features at multiple scales. These features are integrated at multiple levels using 2D entropy based combination scheme to derive a combined map. The combined map is normalised and enhanced using natural logarithm transformation to derive a final saliency map. The experimental results show that the proposed model has achieved better prediction accuracy with significant complexity reduction compared to the existing benchmark models over two large public image datasets.

Iaith wreiddiolSaesneg
TeitlICECS 2020 - 27th IEEE International Conference on Electronics, Circuits and Systems, Proceedings
CyhoeddwrInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronig)9781728160443
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 28 Rhag 2020
Cyhoeddwyd yn allanolIe
Digwyddiad27th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2020 - Glasgow, Y Deyrnas Unedig
Hyd: 23 Tach 202025 Tach 2020

Cyfres gyhoeddiadau

EnwICECS 2020 - 27th IEEE International Conference on Electronics, Circuits and Systems, Proceedings

Cynhadledd

Cynhadledd27th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2020
Gwlad/TiriogaethY Deyrnas Unedig
DinasGlasgow
Cyfnod23/11/2025/11/20

Dyfynnu hyn