Letter-level Online Writer Identification
Zelin Chen, Hong-Xing Yu, Ancong Wu, Wei-Shi Zheng

TL;DR
This paper introduces a novel letter-level online writer identification method that works with minimal input, addressing style variability and enabling practical applications on mobile devices, supported by a new large-scale dataset.
Contribution
The paper proposes a capture-normalize-aggregate framework with a multi-branch encoder, a novel normalization layer, and hierarchical attention pooling for letter-level writer identification.
Findings
Effective identification with few letter trajectories.
Robustness to style variations demonstrated.
Superior performance on the new LERID dataset.
Abstract
Writer identification (writer-id), an important field in biometrics, aims to identify a writer by their handwriting. Identification in existing writer-id studies requires a complete document or text, limiting the scalability and flexibility of writer-id in realistic applications. To make the application of writer-id more practical (e.g., on mobile devices), we focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues. Unlike text-\ document-based writer-id which has rich context for identification, there are much fewer clues to recognize an author from only a few single letters. A main challenge is that a person often writes a letter in different styles from time to time. We refer to this problem as the variance of online writing styles (Var-O-Styles). We address the Var-O-Styles in a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Authorship Attribution and Profiling · Natural Language Processing Techniques
