Letter-Level Online Writer Identification

Chen, Zelin; Yu, Hang; Wu, Ancong; Zheng, Wei‐Shi

doi:10.1007/s11263-020-01414-y

Cited by 14 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shaikh et al [14] employed the cross attention and soft attention to concentrate on highly correlated pixel regions of handwriting pairs. Chen et al [11] proposed the Letters and Styles Adapters (LSA) to encode different letters, which were inserted between CNN and LSTM. They also proposed Hierarchical Attention Pooling (HAP) to aggregate features.…”

Section: ) Attention-basedmentioning

confidence: 99%

“…Also, the combination of handcrafted feature extractors and deep neural networks [8]- [10] has been well explored. As attention-based methods have recently become mainstream, several studies [11]- [14] have focused on attention-based methods to enhance modeling in feature space, which are usually combined with CNN. The aforementioned methods have achieved promising performance in page-level or sentence-level scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

RSTC: A New Residual Swin Transformer for Offline Word-Level Writer Identification

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

Writer identification has steadily progressed in recent decades owing to its widespread application. Scenarios with extensive handwriting data such as page-level or sentence-level have achieved satisfactory accuracy, however, word-level offline writer identification is still challenging owing to the difficulty of learning good feature representations with scant handwriting data. This paper proposes a new Residual Swin Transformer Classifier (RSTC), comprehensively aggregating local and global handwriting styles and yielding robust feature representations with single-word images. Local information is modeled by the Transformer Block through interacting strokes. Global information is featurized by holistic encoding using the Identity Branch and Global Block. Moreover, the pre-training technique is exploited to transfer reusable knowledge learned from a task similar to writer identification, strengthening the model's representation of handwriting features. The proposed method is tested on the IAM and CVL benchmark datasets and achieves state-of-the-art performance, which demonstrates RSTC's superior modeling capability on word-level writer identification.

show abstract

Section: ) Attention-basedmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

RSTC: A New Residual Swin Transformer for Offline Word-Level Writer Identification

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Users not only wrote separate digits but also the same 4-digit passwords by finger. Chen et al [3] proposed the LERID database, which is composed of English single-letter.…”

Section: Single Character/digit/letter Datasetsmentioning

confidence: 99%

“…2 Non-public. 3 X, Y, Z, P, T, I r , I s , A z , A t , B respectively denote the x, y, z coordinates, pressure, timestamps, static rendered images, scanned images, azimuth, altitude, and button status.…”

Section: Msds Datasetmentioning

confidence: 99%

See 1 more Smart Citation

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