Entropy-Guided Assessment of Image Retrieval Systems: Advancing Grouped Precision as an Evaluation Measure for Relevant Retrievability

The performance evaluation of Content Based Image Retrieval systems (CBIR), can be considered as a challenging and overriding problem even for human expert users regarding the important numbers CBIR proposed in literature applied to different image databases. automatic measures widely used assess are inspired from general Text (TR) domain such precision recall metrics. This paper proposes new quantitative measure adapted particularity relevant images grouping, which is based on entropy returned images. easy understand implement. A good discriminative power shown through comparative study with existing well-known measures.