Quality Assessment of Despeckling Filters Based on the Analysis of Ratio Images

Abstract

Highlights: What are the main findings? We propose a normalized metric (TDM) that effectively integrates contrast ((Formula presented.)), variance ((Formula presented.)), and Jensen–Shannon Divergence ((Formula presented.)) into a unified quantitative indicator. We combine the analysis of this proposed metric with quality assessment through a novel approach using Image Horizontal Visibility Graphs (IHVG) based on ratio images. What are the implication of the main findings? The proposed approach discriminates between filters that only suppress variance and those that effectively restore the statistical randomness of the ratio images. The proposed quality assessment framework enables the integrated evaluation of image quality by combining statistical descriptors with graph-based texture analysis, providing a more comprehensive characterization of despeckling performance. We present a quantitative and qualitative evaluation of despeckling filters based on a set of Haralick-derived features and the Jensen–Shannon Divergence obtained from ratio images. To that aim, we propose a normalized composite index, called the Texture-Divergence Measurement ((Formula presented.)), that describes the statistical and structural behavior of the filtered images. Complementary qualitative analysis using Image Horizontal Visibility Graphs (IHVGs) confirms the results of the proposed metric. The combination of the proposed (Formula presented.) metric and IHVG visualization provides a robust framework for assessing despeckling performance from both statistical and structural perspectives.