Interactive Query Formulation for Object Search

Snakes provide high-level information in the form of continuity constraints and minimum energy constraints related to the contour shape and image features.

In this paper, we aim at using color invariant gradient information, as image features, to guide the deformation process. We focus on using color snakes for interactive image segmentation for the purpose of contentbased image retrieval. The key idea is to select appropriate subimages of objects (instead of the entire image) on which the image object search will be conducted. After image segmentation, to achieve accurate image object search, weights are assigned to the image features of the selected subimages in accordance to their importance i.e. having high feature frequencies but low overall collection frequencies.

Experiments show that the proposed color invariant snake successfully find object material contours discounting other “accidental” edges types (e.g. shadows, shading and highlight transitions). Furthermore, experiments show that object search using subimages with weighted features yield high retrieval accuracy. The object search scheme is at http://www.wins.uva.nl/research/isis/zomax/.