OFFLINE SIGNATURE VERIFICATION WITH USER BASED AND GLOBAL CLASSIFIERS OF LOCAL FEATURES
Mustafa Berkay Yılmaz
Computer Science, PhD Dissertation, 2015
Assoc. Prof. Berrin YANIKOĞLU (Thesis Advisor), Assoc. Prof. Hakan ERDOĞAN,
Assist. Prof. Kamer KAYA, Prof. Bülent SANKUR, Assist. Prof. Devrim ÜNAY
Date & Time: January 5th, 2015 – 2 PM
Place: FENS L058
Keywords : oﬄine signature, histogram of oriented gradients, local binary
patterns, scale invariant feature transform, user dependent/independent classiﬁers,
support vector machines, user based score normalization
Signature verification deals with the problem of identifying forged signatures of a user from his/her genuine signatures. The difficulty lies in identifying allowed variations in a user’s signatures, in the presence of high intra-class and low inter-class variability (the forgeries may be more similar to a user’s genuine signature, compared to his/her other genuine signatures). The problem can be seen as a non-rigid object matching where classes are very similar. In the field of biometrics, signature is considered a behavioral biometric and the problem possesses further difficulties compared to other modalities (e.g. fingerprints) due to the added issue of skilled forgeries.
A novel oﬄine (image-based) signature veriﬁcation system is proposed in this thesis. In order to capture the signature’s stable parts and alleviate the difficulty of global matching, local features (histogram of oriented gradients, local binary patterns) are used, based on gradient information and neighboring information inside local regions. Discriminative power of extracted features is analyzed using support vector machine (SVM) classiﬁers and their fusion gave better results compared to state-of-the-art. Scale invariant feature transform (SIFT) matching is also used as a complementary approach. Two diﬀerent approaches for classifier training are investigated, namely global and user-dependent SVMs. User-dependent SVMs, trained separately for each user, learn to diﬀerentiate a user’s (genuine) reference signatures from other signatures. On the other hand, a single global SVM trained with diﬀerence vectors of query and reference signatures’ features of all users in the training set, learns how to weight the importance of different types of dissimilarities. The fusion of all classiﬁers achieves a 6.97% equal error rate in skilled forgery tests using the public GPDS-160 signature database.
Former versions of the system have won several signature verification competitions such as first place in 4NSigComp2010 and 4NSigComp2012 (the task without disguised signatures); first place in 4NSigComp2011 for Chinese signatures category; first place in SigWiComp2013 for all categories. Obtained results are better than those reported in the literature. One of the major beneﬁts of the proposed method is that user enrollment does not require skilled forgeries of the enrolling user, which is essential for real life applications.