Multi-scale Discriminant Saliency with Wavelet-based Hidden Markov Tree Modelling

01/31/2013
by   Anh Cat Le Ngo, et al.
0

The bottom-up saliency, an early stage of humans' visual attention, can be considered as a binary classification problem between centre and surround classes. Discriminant power of features for the classification is measured as mutual information between distributions of image features and corresponding classes . As the estimated discrepancy very much depends on considered scale level, multi-scale structure and discriminant power are integrated by employing discrete wavelet features and Hidden Markov Tree (HMT). With wavelet coefficients and Hidden Markov Tree parameters, quad-tree like label structures are constructed and utilized in maximum a posterior probability (MAP) of hidden class variables at corresponding dyadic sub-squares. Then, a saliency value for each square block at each scale level is computed with discriminant power principle. Finally, across multiple scales is integrated the final saliency map by an information maximization rule. Both standard quantitative tools such as NSS, LCC, AUC and qualitative assessments are used for evaluating the proposed multi-scale discriminant saliency (MDIS) method against the well-know information based approach AIM on its released image collection with eye-tracking data. Simulation results are presented and analysed to verify the validity of MDIS as well as point out its limitation for further research direction.

READ FULL TEXT

page 6

page 24

research
01/17/2013

Multiscale Discriminant Saliency for Visual Attention

The bottom-up saliency, an early stage of humans' visual attention, can ...
research
01/14/2013

Wavelet-based Scale Saliency

Both pixel-based scale saliency (PSS) and basis project methods focus on...
research
05/24/2018

Geographical Hidden Markov Tree for Flood Extent Mapping (With Proof Appendix)

Flood extent mapping plays a crucial role in disaster management and nat...
research
07/27/2018

Influence of Image Classification Accuracy on Saliency Map Estimation

Saliency map estimation in computer vision aims to estimate the location...
research
10/17/2018

EMHMM Simulation Study

Eye Movement analysis with Hidden Markov Models (EMHMM) is a method for ...
research
07/31/2018

Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks

Recently, many methods to interpret and visualize deep neural network pr...

Please sign up or login with your details

Forgot password? Click here to reset