-
Essay / Online signature verification based on transfer and...
Signature is one of the behavioral characteristics of humans that can be used to identify an individual. Widely implemented in daily life, the signature enjoys great social acceptance cite{jain1}. The signature was primarily used to verify important documents, such as bank checks. However, in many cases, human eyes cannot distinguish genuine signatures from counterfeit signatures, which will become a serious problem in the security system. Therefore, the need for high-precision automatic signature verification systems is increasing nowadays. Signature verification is divided into two classes based on the type of signature acquisition, online and offline signature verification cite{impedovo1}. Online signature verification uses a digital input device, such as a digital tablet and digital pen, to acquire data during the signing process in the form of sampled signals. On the other hand, offline signature verification performs static data acquisition using a scanner. In this case, the data is represented as images. Handwriting fluctuation, limited number of training data, and difficulty in extracting stable features from signatures are some problems that need to be faced during signature verification. Much online signature verification work has been carried out to find the precise cite{jain1,impedovo1,plamondon1} method. Among these proposed methods, many researchers have directly used the $x$ and $y$ positions of the signatures. However, we consider this not effective because genuine and counterfeit signatures are quite similar in shape and result from the difficulty of the verification process. To overcome the problem, new signature features related to the $x$ and $y$ positions of the signature called forward and backward variances of the signature are...... middle of paper...... Image and Signal Processing, vol. 150, no. 6, pp. 395-401, 2003. ibitem{canggih1}CP Wibowo, P. Thumwarin and T. Matsuura, Online signature verification based on pen movement angles. 32nd International Conference on Simulation Technologies (JSST), 2013. ibitem{taherzadeh1}G. Taherzadeh, R. Karimi et al. Evaluating online signature verification features. 13th International Conference on Advanced Communication Technologies (ICACT), 2011. ibitem{nakanishi1}I. Nakanishi, S. Nakatani et al. Simply partitioned DP matching and threshold equalization in DWT domain online signature verification. International Conference on Frontiers in Handwriting Recognition (ICFHR), 2010. ibitem{yu1}Q. Yu, W. XingXing et al. Distance learning Mahalanobis for DTW-based online signature verification. IEEE International Conference on Information and Automation (ICIA), 2011.