Off-line signature verification based on grey level information using texture features

摘要: A method for conducting off-line handwritten signature verification is described. It works at the global image level and measures grey variations in using statistical texture features. The co-occurrence matrix local binary pattern are analysed used as This begins with a proposed background removal. histogram also processed to reduce influence of different writing ink pens by signers. Genuine samples random forgeries have been train an SVM model skilled testing it. Results reasonable according state-of-the-art approaches that use same two databases: MCYT-75 GPDS-100 Corpuses. combination features those other authors, based on geometric information, promises improvements performance.