Making colors worth more than a thousand words
Jurandy Almeida, Anderson De Rezende Rocha, Ricardo da Silva Torres, Siome Klein Goldenstein · 2008
Content-based image retrieval (CBIR) is a challenging task. Common techniques use only low-level features. However, these solutions can lead to the so-called 'semantic gap' problem: images with high feature similarities may be different in terms of user perception. In this paper, our objective is to retrieve images based on color cues which may present some affine transformations. For that, we present CSIR: a new method for comparing images based on discrete distributions of distinctive color and scale image regions. We validate the technique using images with a large range of viewpoints, partial occlusion, changes in illumination, and various domains.