隐马尔可夫模型下视频手写签名认证算法研究  

Research on Video Based Handwritten Signature Verification Algorithm Based on HMM Model

作　　者：雷涛[1] 

机构地区：[1]华南师范大学物理与电信工程学院,广州510006

出　　处：《计算机测量与控制》2017年第7期290-293,共4页Computer Measurement &Control

基　　金：广东省省级科技计划项目:基于移动终端及网络的远程智能医疗监护平台(2013B010204019)

摘　　要：为了提高视频手写签名认证的准确率,确保身份认证的严谨性,需要对隐马尔可夫(Hidden Markov Models,HMM)模型下视频手写签名认证算法进行改进设计;使用当前算法对视频手写签名进行认证时,存在认证判断误差大、效率低的问题;提出基于HMM模型下视频手写签名认证算法;该算法将使用Wacom手写板采集手写签名特征点及压力数据,对采集到的手写签名特征与压力数据进行预处理,消除采集过程中环境和手写板产生的影响,并且规范采集的视频手写签名特征位置、尺寸,提取手写签名特征与压力数据,再以HMM模型对已提取的视频手写签名特征点与压力数据进行认证与计算,确定签名的真实度;实验仿真证明,所提算法提高了视频签名认证的性能。In order to improve the accuracy of the handwritten signature verification and ensure the preciseness of the authentication, we need to improve the design of the HMM （Hidden Markov Models） algorithm. When the current algorithm is used to authenticate the handwritten signature, there are many problems such as low error and low efficiency. A video based handwritten signature verification algorithm based on HMM （Hidden Markov Models） model is proposed. The algorithm will use the Wacom tablet collection handwritten signature feature points and pressure data of handwritten signature features and pressure data collected for pretreatment, eliminate the influence of environment in the process of collecting and writing board, and standard video handwriting signature features location, size, feature extraction of handwritten signature and pressure data, and then to the HMM model of the extracted video signature feature points and the pressure data authentication and calculation, to determine the true degree of signature. The simulation results show that the proposed algorithm improves the performance of video signature verification.

关 键 词：隐马尔可夫模型 视频手写签名 签名认证 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]