Offline signature verification using support vectore machine

The analysis of dynamic features for automatic static handwritten signature verification based on the use of gray level values from signature stroke pixels. Rotation invariant uniform local binary patterns and statistical measures from gray level co-occurrence matrices (GLCM) with MCYT and GPDS offline signature corpuses. This project is to measure gray level features robustness when it is distorted by a complex background and also to propose more stable features. The signature models are trained with genuine signatures on white background and tested with other genuine and forgeries mixed with different backgrounds. The results for local binary patterns (LBP) or local derivative and directional patterns are more robust than rotation invariant uniform LBP or GLCM features to the gray level distortion when using a support vector machine with histogram oriented kernels as a classifier.