AnjanDutta/SignatureVerificationCompactCorrelation

This work considers the offline signature verification problem which is regarded to be an important research line in the field of pattern recognition. In this work we propose hybrid features that consider the local attributes and their global statistics in the signature image. This has been done by creating a vocabulary of HOGs. We impose weights on these local features based on the height information of water reservoirs obtained from the signature. Spatial information between local features are thought to play a vital role in considering the geometry of the signatures which distinguishes the originals from the forged ones. Nevertheless, learning a compact set of features based on visual words e.g. doublets and triplets, remains a challenging problem as possible combinations of visual words grow exponentially. To avoid the explosion of size, we create a code of local pairwise features which are represented as joint descriptors. Local features are paired based on the edges of a graph representation built upon the Delaunay triangulation. We reveal the advantage of combining both type of visual codebooks (order one and pairwise) for signature verification task. This is validated through a encouraging result on two benchmark datasets viz CEDAR and GPDS.