SCUT-MMSIG: A Multimodal Online Signature Database

Lu, Xinyi; Fang, Yuxun; Kang, Wenxiong; Wang, Zhiyong; Feng, David Dagan

doi:10.1007/978-3-319-69923-3_78

Cited by 10 publications

(27 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They evaluated the verification performance under three scenarios: intra-device, inter-device, and mixed writing-tool. Lu et al [25] proposed SCUT-MMSIG, a Chinese signature dataset that possesses three modalities: mobile, tablet, and in-air. 50 writers wrote 20 genuine and forged signatures in each modality, respectively.…”

Section: Signature Datasetsmentioning

confidence: 99%

“…Compared with the aforementioned online Chinese signature dataset, our proposed MSDS-ChS subset is more than eight times larger than the one with the largest number of users (SCUT-MMSIG [25], 50 users). The MSDS-TDS subset firstly covers handwritten Token Digit String, which is more common than separate digits and worthy of in-depth exploration.…”

Section: Single Character/digit/letter Datasetsmentioning

confidence: 99%

“…Although handwriting verification has been rapidly developed, the verification performances in specific scenarios are still unsatisfactory owing to the small sizes of datasets and the limited biometric mediums. For online Chinese signature verification, the largest existing dataset [25] has only 50 users. However, DeepSignDB [40], the largest online signature dataset in the Western language, possesses 1526 users and almost 70,000 samples.…”

Section: Appendixmentioning

confidence: 99%

“…DeepSignDB [40], the largest online signature database in the Western language, contains 1526 users and almost 70,000 samples. But the existing public online Chinese signature datasets [25,24,47] are considerably smaller, with no more than 50 registered users, hindering researchers from in-depth explorations of Chinese signature verification.…”

Section: Introductionmentioning

confidence: 99%

“…• MSDS-ChS is the largest publicly available Chinese signature dataset, whose size is at least eight times larger than the previous online Chinese signature datasets [25]. • MSDS-TDS is the first large-scale Token Digit String dataset that studies the effectiveness of handwritten TDS.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification

Zhang¹,

Jiang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Although online handwriting verification has made great progress recently, the verification performances are still far behind the real usage owing to the small scale of the datasets as well as the limited biometric mediums. Therefore, this paper proposes a new handwriting verification benchmark dataset named Multimodal Signature and Digit String (MSDS), which consists of two subsets: MSDS-ChS (Chinese Signatures) and MSDS-TDS (Token Digit Strings), contributed by 402 users, with 20 genuine samples and 20 skilled forgeries per user per subset. MSDS-ChS consists of handwritten Chinese signatures, which, to the best of our knowledge, is the largest publicly available Chinese signature dataset for handwriting verification, at least eight times larger than existing online datasets. Meanwhile, MSDS-TDS consists of handwritten Token Digit Strings, i.e, the actual phone numbers of users, which have not been explored yet. Extensive experiments with different baselines are respectively conducted for MSDS-ChS and MSDS-TDS. Surprisingly, verification performances of state-of-the-art methods on MSDS-TDS are generally better than those on MSDS-ChS, which indicates that the handwritten Token Digit String could be a more effective biometric than handwritten Chinese signature. This is a promising discovery that could inspire us to explore new biometric traits. The MSDS dataset is available at https://github.com/HCIILAB/MSDS.

show abstract

Section: Signature Datasetsmentioning

confidence: 99%

Section: Single Character/digit/letter Datasetsmentioning

confidence: 99%