Offline signature verification through probabilistic neural network
Ooi Shih Yin, Andrew Beng Jin Teoh, Hiew Bee Yan, Ying Han Pang · Digital Library (University of West Bohemia) · 2010
In this paper, we show the positive potential of verifying the offline handwritten signatures through discrete Radon transform (DRT), principle component analysis (PCA) and probabilistic neural network (PNN). Satisfactory results are obtained with 1.51%, 3.23%, and 13.07% equal error rate (EER) for random, casual, and skilled forgeries respectively on our independent database.