A Multi Criteria Decision Making Based Approach for Semantic Image Annotation

This paper presents a novel model for automatic image annotation that integrates regional contexts and visual topics using a multi-criteria decision-making (MCDM) approach. It addresses limitations in existing techniques by focusing on the relationships between image regions, enhancing semantic understanding for better annotation. The proposed method, tested on the 5k Corel dataset, demonstrates improved effectiveness in image annotation compared to traditional models.