CAJ | 학술논문

提出一种新的曲线相似计算模型，用于在线签名身份认证。将在线签名轨迹数据看做平面曲线，从曲线相似性定义、相似变换及相似距离给出了曲线相似计算模型框架。依照参考签名曲线有效点数，对比较签名曲线进行重采样；签名曲线相似度量过程采用分段匹配方法，在每段比较曲线待匹配区间内，利用遗传算法搜索与参考曲线对应段的最优匹配，获得分段的相似距离，以此计算分段相似得分；将各段相似得分的平均值作为两条曲线的相似度量。选用 SVC2004 Task1和 SUSig Blind 数据集对算法进行测试，等误率分别为10．92％和2．89％。
제출일충신적곡선상사계산모형，용우재선첨명신빈인증。장재선첨명궤적수거간주평면곡선，종곡선상사성정의、상사변환급상사거리급출료곡선상사계산모형광가。의조삼고첨명곡선유효점수，대비교첨명곡선진행중채양；첨명곡선상사도량과정채용분단필배방법，재매단비교곡선대필배구간내，이용유전산법수색여삼고곡선대응단적최우필배，획득분단적상사거리，이차계산분단상사득분；장각단상사득분적평균치작위량조곡선적상사도량。선용 SVC2004 Task1화 SUSig Blind 수거집대산법진행측시，등오솔분별위10．92％화2．89％。
A new curve similarity calculation model is presented for online signature verification.Conside-ring online signature trajectory data as a plane curve,a curve similarity model is built based on the similarity definition,similarity transformation and curve similarity distance.The comparison signature curve is re-sampled according to the effective point number of the reference one.In the calculation of curve similarity,the sectional matching is applied.In the range of each comparison curve interval to match,the sectional curve similarity dis-tance is calculated by the genetic algorithm.The optimal sectional matching is found in the corresponding sec-tion of the reference curve.Then the sectional similarity distance is obtained and the estimate sectional similarity score is calculated.The mean of all similarity scores is defined as the curve similarity measure.The proposed al-gorithm is tested,and the equal error rates are 10.92% and 2.89% for SVC2004 Task1 and SUSIG Blind data-bases,respectively.