Combining block and corner features for content-based trademark retrieval

Abstract

In order to retrieve a similarly look trademark from a large trademark database, an automatic content based trademark retrieval method using block hit statistic and corner Delaunay Triangulation features was proposed. The block features are derived from the hit statistic on a series of concentric ellipse. The corners are detected based on an enhanced SUSAN (Smallest Univalue Segment Assimilating Nucleus) algorithm and the Delaunay Triangulation of corner points are used as the corner features. Experiments have been conducted on the MPEG-7 Core Experiment CE-Shape-1 database of 1 400 images and a trademark database of 2 000 images. The retrieval results are very encouraging.