A computational model of visual attention. [Dataset]

Abstract

This dataset is supplementary to the full thesis, which is available on OpenAIR: http://hdl.handle.net/10059/2443. The dataset is compiled of two folders. The first folder ("Evaluation metrics") contains four MATLAB files in .m format and one plain text README file. The second folder ("Visual Saliency Model (MATLAB)") contains seven MATLAB files in .m format, seven image files in .jpg/.jpeg format, three image files in .bmp format and one plain text README file. The abstract for the thesis includes the following extract: This thesis proposes a novel computational model of visual attention that achieves higher prediction accuracy with low computational complexity. A new bottom-up visual attention model based on in-focus regions is proposed. The results show that the model achieves higher prediction accuracy with a lower computational complexity compared to the state-of-the-art visual attention models.

Citation

CHILUKAMARI, J. 2017. A computational model of visual attention. [Dataset]

• Deposit Date: Aug 31, 2017
• Publicly Available Date: Aug 31, 2017
• Keywords: Visual saliency; Saliency detection; Infocus; DCT; Frequency saliency; Fixation prediction; Attention; Visual attention models; Saliency model; Face saliency
• Public URL: http://hdl.handle.net/10059/2481
• Related Public URLs: http://hdl.handle.net/10059/2443 ; http://hdl.handle.net/10059/2477 ; http://hdl.handle.net/10059/2478 ; http://hdl.handle.net/10059/2479
• Type of Data: MATLAB files, image files and supporting text files.
• Collection Date: Feb 28, 2017
• Contract Date: Aug 31, 2017