Abstract:
A number of biometric methods can be used to authenticate a human identity such as using fingerprint detection, face detection, iris inspection and voice recognition. The verification of the signature of a human is the most prominent and prevalent method among those. The banking and insurance sector manually uses this verification method. It is a critical biometric attribute, which may differ from time to time due to the age and emotional state of the person. Because of the absence of the time feature of the signature, offline signature verification has a risk than online signature verification. The paper introduces six features for an alternate solution. They include scale and rotation invariant such as signature pixel ratio of concentric circles and number of cross points while others are rotation variant such as baseline slant angle, aspect ratio, normalized area and slope of the line connecting center of gravities of left and right halves of the bounding box of the signature. Back-propagation neural network is used to train and test the signature images. Experimentation and results of this methodology presents the possibility of using this system in relevant sectors.
