Wavelet-based Scale Saliency

TL;DR

This paper introduces wavelet-based scale saliency (WSS), a novel model that uses wavelet sub-bands as basis descriptors for multiscale data analysis, and compares its effectiveness with existing methods using eye-tracking data.

Contribution

It extends pixel-based scale saliency models to basis-projected descriptors by developing mathematical models for wavelet-based saliency, including various wavelet transforms and best basis selection.

Findings

WSS generates saliency maps comparable to other methods.

Quantitative evaluation shows WSS achieves high ROC and AUC scores.

Qualitative analysis confirms WSS aligns well with human eye-tracking data.

Abstract

Both pixel-based scale saliency (PSS) and basis project methods focus on multiscale analysis of data content and structure. Their theoretical relations and practical combination are previously discussed. However, no models have ever been proposed for calculating scale saliency on basis-projected descriptors since then. This paper extend those ideas into mathematical models and implement them in the wavelet-based scale saliency (WSS). While PSS uses pixel-value descriptors, WSS treats wavelet sub-bands as basis descriptors. The paper discusses different wavelet descriptors: discrete wavelet transform (DWT), wavelet packet transform (DWPT), quaternion wavelet transform (QWT) and best basis quaternion wavelet packet transform (QWPTBB). WSS saliency maps of different descriptors are generated and compared against other saliency methods by both quantitative and quanlitative methods. Quantitative results, ROC curves, AUC values and NSS values are collected from simulations on Bruce and Kootstra image databases with human eye-tracking data as ground-truth. Furthermore, qualitative visual results of saliency maps are analyzed and compared against each other as well as eye-tracking data inclusive in the databases.