Evaluation method improves image quality assessment consistency with human visual system, utilizing local and global consistency metrics.
Abstract Due to the complexity of fused images, a single metric cannot provide a comprehensive assessment in all cases. In this paper, an evaluation method based on MMEC (Multi-Metric Extraction and Combination) is proposed. Firstly, the principle of Local and Global Consistency (LGC) is proposed. Secondly, this principle is used to extract metrics from the Total Metric Set (TMS) to form a Suitable Metric Set (SMS). Then, the mapping conditions of the composite metrics are studied. Finally, a combination mapping is constructed to convert multiple metrics into a scalar for objective evaluation. Experiments on five sets of images show that our method is consistent with the Human Visual System (HVS).
No takes yet. Share an insight, caveat, or question.
Weitong Li (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: