This model of bottom-up saliency is based on the forward whitening of low level features, from an overcomplete representation of the image. It is hence, based on a simple adaptive coding approach that provides short-term contextual adaptation to scene content.



It has been developed as part of the research work conducted for the achievement of the PhD. degree by A. Garcia-Diaz, under the direction of X. R. Fdez-Vidal and X. M. Pardo. A complete description of the model and an analysis of its results and implications is given in the Ph.D. thesis entitled "Modeling early visual coding and saliency through adaptive whitening: plausibility, assessment, and applications" (See publications section).

• Prediction of human fixations


• Reproduction of psychophysical results


• Saliency-based segmentation

Usage:

• im = imread('image.jpg');
  SaliencyMap = aws(im, 0.5);
  

or:


• SaliencyMap = aws('image.jpg', 0.5);
  

1. An RGB image
   
2. Rescaling factor
   

1. Leboran, V; Garcia-Diaz, A; Fdez-Vidal, X and Pardo, X. Dynamic Whitening Saliency. In IEEE Transactions on Pattern Analysis and Machine Intelligence, PP (99): 1-1, 2016.

2. Garcia-Diaz, A.; Leborán, V.; Fdez-Vidal, X. R. and Pardo, X. M.. On the relationship between optical variability, visual saliency, and eye fixations: A computational approach. In Journal of Vision, 12 (6), 2012. doi.. 
3. Garcia-Diaz, A.; Fdez-Vidal, X. R; Pardo, X. M and Dosil, R.. Saliency from hierarchical adaptation through decorrelation and variance normalization. In Image and Vision Computing, 30 (1): 51-64, 2012. doi.. 

4. Garcia-Diaz, A.; Fdez-Vidal, X. R; Pardo, X. M and Dosil, R.. Local Energy Variability as a Generic Measure of Bottom-Up Salience. In Pattern Recognition Techniques, Technology and Applications, pages 1-24, I-Tech Education and Publishing, Vienna, Austria, 2008. pdf.. 

5. Leborán Alvarez, V.; García-Díaz, A.; Fdez-Vidal, X. R. and Pardo, X. M.. Dynamic Saliency from Adaptative Whitening. In Natural and Artificial Computation in Engineering and Medical Applications, pages 345-354, Springer Berlin Heidelberg, Lecture Notes in Computer Science 7931, 2013.

6. Garcia-Diaz, A.; Fdez-Vidal, X. R; Pardo, X. M and Dosil, R.. Saliency Based on Decorrelation and Distinctiveness of Local Responses. In Computer Analysis of Images and Patterns, pages 261-268, Springer Berlin/Heidelberg, Lecture Notes in Computer Science 5702, 2009. pdf.. 
7. Garcia-Diaz, A.; Fdez-Vidal, X.; Pardo, X. and Dosil, R.. Decorrelation and Distinctiveness Provide with Human-Like Saliency. In Advanced Concepts for Intelligent Vision Systems, pages 343-354, Springer Berlin/Heidelberg, Lecture Notes in Computer Science 5807, 2009. pdf.. 

8. Garcia-Diaz, A.; Fdez-Vidal, X. R; Dosil, R. and Pardo, X. M. A novel model of bottom-up visual attention using local energy. In Computational Vision and Medical Image Processing. Ed Taylor & Francis (VIPimage’07), pages 255-260, 2007.
9. Garcia-Diaz, A.; Fdez-Vidal, X. R; Dosil, R. and Pardo, X. M. Local energy saliency for bottom up visual attention. In Proc. IASTED International Conference on Visualization, Imaging and Image Processing (VIIP’07)., pages 154-159, 2007.

10. Garcia-Diaz, A.. La energía local como medida de saliencia visual. Master's Thesis, Facultade de Física, Universidade de Santiago de Compostela, 2007.

11. Garcia-Diaz, A.. Modeling early visual coding and saliency through adaptive whitening: plausibility, assessment and applications. Ph.D. Thesis, Higher Technical Engineering School, University of Santiago de Compostela, 2011. pdf.. 

1. SaliencyEvaluation page by Ali Borji and Laurent Itti, (2010).
2. Computational Attention: Saliency modeling and applications. University of Mons.(Belgium)
3. Hae Jong SEO's Website. University of California at Santa Cruz.(USA).