Robertson Joshua, Guest Richard
School of Engineering and Digital Arts, University of Kent, Canterbury CT2 7NT, UK.
Hum Mov Sci. 2015 Oct;43:169-82. doi: 10.1016/j.humov.2015.06.003. Epub 2015 Jun 18.
Dynamic Signature Verification (DSV) is a biometric modality that identifies anatomical and behavioral characteristics when an individual signs their name. Conventionally signature data has been captured using pen/tablet apparatus. However, the use of other devices such as the touch-screen tablets has expanded in recent years affording the possibility of assessing biometric interaction on this new technology. To explore the potential of employing DSV techniques when a user signs or swipes with their finger, we report a study to correlate pen and finger generated features. Investigating the stability and correlation between a set of characteristic features recorded in participant's signatures and touch-based swipe gestures, a statistical analysis was conducted to assess consistency between capture scenarios. The results indicate that there is a range of static and dynamic features such as the rate of jerk, size, duration and the distance the pen traveled that can lead to interoperability between these two systems for input methods for use within a potential biometric context. It can be concluded that this data indicates that a general principle is that the same underlying constructional mechanisms are evident.
动态签名验证（DSV）是一种生物识别方式，可在个人签名时识别其解剖学和行为特征。传统上，签名数据是使用笔/数位板设备采集的。然而，近年来，诸如触摸屏平板电脑等其他设备的使用有所增加，这为评估这项新技术上的生物识别交互提供了可能性。为了探索用户用手指签名或滑动时采用DSV技术的潜力，我们报告了一项将笔和手指生成的特征进行关联的研究。通过研究参与者签名和基于触摸的滑动手势中记录的一组特征之间的稳定性和相关性，进行了统计分析以评估不同采集场景之间的一致性。结果表明，存在一系列静态和动态特征，如急动率、大小、持续时间和笔移动的距离，这些特征可使这两种系统在潜在生物识别环境中的输入方法实现互操作性。可以得出结论，这些数据表明一个普遍原则，即相同的潜在构造机制是明显的。
