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

TL;DR

This paper introduces a multi-scale discriminant saliency method using wavelet features and Hidden Markov Tree modeling to improve visual attention prediction, validated through quantitative and qualitative evaluations.

Contribution

The paper proposes a novel multi-scale saliency detection approach combining wavelet features and HMT, enhancing the discrimination of salient regions across scales.

Findings

MDIS outperforms AIM in quantitative metrics

The method effectively captures multi-scale saliency features

Limitations identified for future research

Abstract

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.