From BoVW to VLAD with KAZE features : Offline signature verification considering cognitive processes of forensic experts
From BoVW to VLAD with KAZE features : Offline signature verification considering cognitive processes of forensic experts
复制标题
从 BoVW 到具有 KAZE 功能的 VLAD：考虑法医专家认知过程的离线签名验证
DOI：
10.1016/j.patrec.2018.05.019
复制
发表时间：
2018
影响因子：
5.1
通讯作者：
大川 学
中科院分区：
文献类型：
--
作者：
笹岡由唯;上園波輝;上田真也;高田拓;水口 貴詞;大川 学
手写签名用于身份认证的广泛使用导致了对自动验证系统的需求。然而，与人类分析相比，自动化系统的性能还有改进的空间，特别是在各种条件下，法证文件检查员 (FDE) 的性能。由于分析的任何不准确都可能导致严重的问题，因此需要进一步的研究来提高性能。在本研究中，为了提高各种写入条件下离线签名验证的性能，采用了使用视觉词袋（BoVW）和本地聚合描述符向量（VLAD）的特征编码方法的新方法。所提出的方法考虑了 FDE 用于提高性能的认知过程的当前知识。所提出的方法结合了基于 BoVW 和 VLAD 的方法以及局部特征来模拟 FDE 的认知过程以进行特征提取。此外，在笔划和背景空间中检测到的KAZE特征被用作局部特征以增强判别力。使用公开可用的 CEDAR 和 MCYT-75 签名数据集证明了所提出方法的性能。
The widespread use of handwritten signatures for identity authentication has resulted in a need for automated verification systems. However, there is room for improvement in the performance of automated systems compared to human analysis, particularly that of forensic document examiners (FDEs), under a wide range of conditions. As any inaccuracy in analysis can cause serious problems, further research is required to improve performance. In this study, to improve the performance of offline signature verification under various writing conditions, new approaches using feature encoding methods of a bag-of-visual words (BoVW) and a vector of locally aggregated descriptors (VLAD) are adopted. The proposed method considers current knowledge about the cognitive processes used by FDEs to improve performance. The proposed method incorporates an approach based on BoVW and VLAD with local features to mimic the cognitive processes of FDEs for feature extraction. In addition, KAZE features detected in strokes and background space are employed as local features to enhance discriminative power. The performance of the proposed approach is demonstrated using the publicly-available CEDAR and MCYT-75 signature datasets.