IEEE Trans Pattern Anal Mach Intell. 2019 Dec;41(12):2807-2819. doi: 10.1109/TPAMI.2018.2869163. Epub 2018 Sep 10.
Many features have been proposed in on-line signature verification. Generally, these features rely on the position of the on-line signature samples and their dynamic properties, as recorded by a tablet. This paper proposes a novel feature space to describe efficiently on-line signatures. Since producing a signature requires a skeletal arm system and its associated muscles, the new feature space is based on characterizing the movement of the shoulder, the elbow and the wrist joints when signing. As this motion is not directly obtained from a digital tablet, the new features are calculated by means of a virtual skeletal arm (VSA) model, which simulates the architecture of a real arm and forearm. Specifically, the VSA motion is described by its 3D joint position and its joint angles. These anthropomorphic features are worked out from both pen position and orientation through the VSA forward and direct kinematic model. The anthropomorphic features' robustness is proved by achieving state-of-the-art performance with several verifiers and multiple benchmarks on third party signature databases, which were collected with different devices and in different languages and scripts.
许多在线签名验证方法都提出了各种特征。一般来说，这些特征依赖于在线签名样本的位置及其动态特性，这些特性由手写板记录。本文提出了一种新的特征空间，以有效地描述在线签名。由于签名需要骨骼手臂系统及其相关肌肉，因此新的特征空间基于签名时肩部、肘部和腕关节的运动特征来构建。由于这种运动不能直接从数字手写板获得，因此新特征是通过虚拟骨骼手臂 (VSA) 模型计算得出的，该模型模拟了真实手臂和前臂的结构。具体来说，VSA 运动通过其 3D 关节位置及其关节角度来描述。这些拟人化特征是通过 VSA 正向和直接运动学模型从笔的位置和方向计算得出的。通过使用多个验证器和多个第三方签名数据库的基准测试，证明了拟人化特征的鲁棒性，这些数据库是使用不同的设备和不同的语言和脚本收集的。
