Semantic Mapping of Image Databases using Perceptual Similarity

Semantic mapping of image databases is explored based on a human-centered approach for judging visual similarity. The management is pursued using a standard psychophysical experiment followed by a well-suited data analysis methodology. The end-result is a cognitive discriminative biplot, which is a visualization of the intrinsic organization of the image database best reflecting the user's perception. The discriminating power of the introduced biplot constitutes it an appealing tool for image retrieval and a flexible interface for visual data mining tasks.