Image indexation and content based search using pre-attentive similarities

We introduce in this paper the general architecture of an image search engine based on pre-attentive similarities. The components of this system are presented and some of them are detailled. Our approach is based on the extraction of interest points using a multiresolution technique. The spatial distribution of these points is embeded in bidimensional histograms of classic features the rst ve di erential invariants. A relevant feedback including the user is introduced in order to overcome the limitations of any pre-attentive similarities based scheme. Keywords Image indexation, interest points, pre-attentive similarity, relevant feedback, content-based search.

• Type: Conference
• Year: 2000
• Where: RIAO
• Authors: Alexander Heinrichs, Dimitri Koubaroulis, Barbara Levienaise-Obadia, Paulo Rovida, Jean-Michel Jolion
• Keywords: Image Search Engine, Pre-attentive Similarities, Relevant Feedback, RIAO 2000, RIAO 2007