In this paper we present a system for offline signature verification based on Shape Context Descriptors. The system input are binarized images of handwritten signatures from GPDS database available for non-commercial research. During preprocessing each signature image is thinned using KMM algorithm in order to obtain 1-pixel wide skeleton. The feature vector is built from Shape Context Descriptors computed for selected points on skeletonized signature line. The verification process is based on the distance measure that uses Shape Context Descriptors. The presented system is evaluated using random and skilled forgeries with shared and user-specific thresholds.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.