A low-complexity wavelet-based visual saliency model to predict fixations.
Narayanaswamy, Manjula; Zhao, Yafan; Fung, Wai Keung; Fough, Nazila
Wai Keung Fung
Dr Nazila Fough email@example.com
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.
NARAYANASWAMY, M., ZHAO, Y., FUNG, W.K. and FOUGH, N. 2020. A low-complexity wavelet-based visual saliency model to predict fixations. In Proceedings of 27th Institute of Electrical and Electronic Engineers (IEEE) International conference on electronics, circuits and systems 2020 (ICECS 2020), 23-25 November 2020, [virtual conference]. Piscataway: IEEE [online], article ID 9294905. Available from: https://doi.org/10.1109/ICECS49266.2020.9294905
|Conference Name||27th Institute of Electrical and Electronic Engineers (IEEE) International conference on electronics, circuits and systems 2020 (ICECS 2020)|
|Conference Location||[virtual conference]|
|Start Date||Nov 23, 2020|
|End Date||Nov 25, 2020|
|Acceptance Date||Sep 18, 2020|
|Online Publication Date||Dec 28, 2020|
|Publication Date||Dec 28, 2020|
|Deposit Date||Jan 28, 2021|
|Publicly Available Date||Jan 28, 2021|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Keywords||Visual saliency model; Fixation prediction; Discrete wavelet transform; Image entropy|
NARAYANASWAMY 2020 A low-complexity wavelet (AAM)
You might also like
A computational visual saliency model for images.
Pipeline leakage detection and characterisation with adaptive surrogate modelling using particle swarm optimisation.
A fuzzy cooperative localisation framework for underwater robotic swarms.