Effect of alignment and multiple-scale features in offline signature verification

We present an offline signature verification system based on a signature´s local histogram features. Test signature is divided into zones using both the Cartesian and log polar coordinate systems and histogram of oriented gradients (HOG) is calculated for each zone. Verification is considered as a two-class classification problem and for this purpose, a user independent Support Vector Machine (SVM) model is trained using both genuine and skilled forgery signatures of a completely different set of people than those in the test set. For each feature type, a single SVM model which learns the differences of query and reference signatures´ feature vectors, is trained. The fusion of all classifiers, using skilled forgeries as negative test examples, achieves a 24.30% equal error rate in the GPDS-160 signature database, with 5 references.