Image-based handwritten signature verification using hybrid methods of discrete Radon transform, principal component analysis and probabilistic neural network

Dynamic variable is introduced to static signature images with DRT reconstruction.Feature data length is reduced through linear compression (PCA).PNN is feasible to filter the skilled forgery from the genuine signature.Time complexity is decreased notably with one-training-sample scheme. Image-based handwritten signature verification is important in most of the financial transactions when a hard copy of signature is needed. Considering the lack of dynamic information from static signature images, we proposed a working framework through hybrid methods of discrete Radon transform (DRT), principal component analysis (PCA) and probabilistic neural network (PNN). The proposed framework aims to distinguish forgeries from genuine signatures based on the image level. Extensive experiments are conducted on our own independent signature database, and a public signature database - MYCT. Equal error rates (EER) of 1.51%, 3.23% and 13.07% are reported, respectively, for random, casual and skilled forgeries of our own database. When working on the MYCT signature database, our proposed approach manages to achieve an EER of 9.87% with 10 training samples.