期刊
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
卷 17, 期 -, 页码 2198-2212出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2022.3180219
关键词
Handwriting recognition; Feature extraction; Task analysis; Training; Deep learning; Benchmark testing; Adaptive systems; Dynamic signature verification; deep representation learning; convolutional recurrent adaptive network; dynamic time warping; soft-DTW
资金
- National Natural Science Foundation of China (NSFC) [61936003]
- Natural Science Foundation of Guangdong Province (GD-NSF) [2017A030312006, 2021A1515011870]
This paper presents an enhanced approach for dynamic time warping (DTW) by incorporating deep learning techniques in dynamic signature verification. The proposed method utilizes a convolutional recurrent adaptive network (CRAN) to process dynamic signatures and incorporates soft-DTW distances into the loss function for optimization. Experimental results show that the method achieves state-of-the-art performance on several benchmarks and wins first place in the ICDAR 2021 competition for online signature verification.
Dynamic time warping (DTW) is a popular technique for sequence alignment, and is the de facto standard for dynamic signature verification. In this paper, we go a significant step further to enhance DTW with the capability of deep representation learning, and propose an end-to-end trainable Deep soft-DTW (DsDTW) model for dynamic signature verification. Specifically, we design a convolutional recurrent adaptive network (CRAN) to process dynamic signatures, and utilize it to provide robust and discriminative local representations as inputs for DTW. As DTW is not fully differentiable with regard to its inputs, we introduce its smoothed formulation, soft-DTW, and incorporate the soft-DTW distances of signature pairs into the loss function for optimization. Because soft-DTW is differentiable, the proposed DsDTW is end-to-end trainable, and achieves an elegant integration of CRAN deep learning model and traditional DTW mechanism. Our method achieves state-of-the-art performance on several public benchmarks, and has won first place in the ICDAR 2021 competition for online signature verification. Source codes of DsDTW is available at https://github.com/KAKAFEI123/DsDTW.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据