A Low-complexity Wavelet-based Visual Saliency Model to Predict Fixations
Fung, Wai Keung
Wedi’i wahardd nes
MetadataDangos cofnod eitem llawn
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.
2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS 2020);
M. Narayanaswamy, Y. Zhao, W. K. Fung and N. Fough (2020) "A Low-complexity Wavelet-based Visual Saliency Model to Predict Fixations," 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), Glasgow, Scotland, UK, 2020, pp. 1-4, doi: 10.1109/ICECS49266.2020.9294905.
Dynodwr Gwrthrych Digidol (DOI)https://doi.org/10.1109/ICECS49266.2020.9294905
Conference paper published in proceedings of 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS) available at https://doi.org/10.1109/ICECS49266.2020.9294905
Hawliau© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Cardiff Metropolitan University (Grant ID: Cardiff Metropolian (Internal))
Yn dangos eitemau sy’n perthyn drwy deitl, awdur, pwnc a chrynodeb.
Fuller, Jack (Cardiff Metropolitan University, 2014)Research into the sport-confidence model (Vealey, Hayashi, Garner-Holman, & Giacobbi, 1998) has mainly investigated the salience of sources amongst individual sport athletes and identified differentiations between gender ...
Cazeaux, Clive (Taylor and Francis, 2015-12-31)Images in science are often beautiful but their beauty cannot be explained using traditional aesthetic theories. Available theories either rely upon concepts antithetical to science, e.g. regularity as an index of God’s ...
Hodgetts, Helen M.; Vachon, François; Chamberland, C.; Tremblay, Sébastian (Elsevier, 2017-05-30)While the development of intelligent technologies in security surveillance can augment human capabilities, they do not replace the role of the operator entirely; as such, when developing surveillance support it is critical ...