Logo recognition using geometric invariants

The problem of logo recognition is of great interest in the document domain, especially for databases, because of its potential for identifying the source of the document and its generality as a recognition problem. By recognizing the logo we obtain semantic information about the document, which may be useful in deciding whether or not to analyze the textual components. In this paper, we present a multi-level staged approach to logo recognition which uses global invariants to prune the database and local afine invariants to obtain a more refined match. We obtain an invariant signature which can be used for matching under a variety of transformations. We provide a method of computing Euclidean invariants, and show how to extend them to capture similarity, afine and projective invariants when necessary. We implement feature detection, feature extraction and local invara'ant algorithms and successfully demonstrate the approach on a small database.