Online Signature Verification Based on Shape Context and Function Features
Online signature verification is becoming quite attractive due to its potential applications.In this paper,we present a method using shape context and function features as well as cascade structure for accurate online signature verification.Specifically,in the first stage features of shape context are extracted and classification is made based on distance metric.Only the input passing by the first stage will be further verified using a set of function features and Dynamic Time Warping(DTW).We also incorporate shape context into DTW get a more accurate matching.The proposed method is tested on SVC2004 database comprising a total of 80 individuals and 3,200 signatures.Experiment result achieves an Equal Error Rate of 2.45%demonstrating the effectiveness of the proposed method.
Online signature verification Shape context Function features Cascade structure
Yu Jia Linlin Huang
Beijing Jiaotong University,No.3 Shangyuancun,Beijing,China
国际会议
广州
英文
62-73
2018-11-23（万方平台首次上网日期，不代表论文的发表时间）