paper-with-me

홈 › Papers

Well-Conditioned Polynomial Representations for Mathematical Handwriting Recognition

2025-09-13 · Robert M. Corless, Deepak Singh Kalhan, Stephen M. Watt arxiv

Previous work has made use of a parameterized plane curve polynomial representation for mathematical handwriting, with the polynomials represented in a Legendre or Legendre-Sobolev graded basis. This provides a compact geometric representation for the digital ink. Preliminary results have also been shown for Chebyshev and Chebyshev-Sobolev bases. This article explores the trade-offs between basis choice and polynomial degree to achieve accurate modeling with a low computational cost. To do this, we consider the condition number for polynomial evaluation in these bases and bound how the various inner products give norms for the variations between symbols.

📄 PDF Abstract BibTeX arXiv:2509.10815

Code (0)

등록된 구현이 없습니다.

Tasks

Handwriting Recognition

Similar Papers 제목 키워드 기반

A First Look at Chebyshev-Sobolev Series for Digital Ink

2024-08-04 · Deepak Singh Kalhan, Stephen M. Watt

Considering digital ink as plane curves provides a valuable framework for various applications, including signature verification, note-taking, and mathematical handwriting recognition. These plane curves can be obtained …

Handwriting Recognition

Text and Style Conditioned GAN for Generation of Offline Handwriting Lines

2020-09-01 · Brian Davis, Chris Tensmeyer, Brian Price, Curtis Wigington 외

This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or single-word images, this model generates enti…

Handwriting generation

Sampling and Ranking for Digital Ink Generation on a tight computational budget

2023-06-02 · Andrei Afonin, Andrii Maksai, Aleksandr Timofeev, Claudiu Musat

Digital ink (online handwriting) generation has a number of potential applications for creating user-visible content, such as handwriting autocompletion, spelling correction, and beautification. Writing is personal and u…

Handwriting generationSpelling Correction

The SWAG Algorithm; a Mathematical Approach that Outperforms Traditional Deep Learning. Theory and Implementation

2018-11-28 · Saeid Safaei, Vahid Safaei, Solmazi Safaei, Zerotti Woods 외

The performance of artificial neural networks (ANNs) is influenced by weight initialization, the nature of activation functions, and their architecture. There is a wide range of activation functions that are traditionall…

Learning Theory

A Transformer Architecture for Online Gesture Recognition of Mathematical Expressions

2022-11-04 · Mirco Ramo, Guénolé C. M. Silvestre

The Transformer architecture is shown to provide a powerful framework as an end-to-end model for building expression trees from online handwritten gestures corresponding to glyph strokes. In particular, the attention mec…

Gesture RecognitionHandwriting Recognitionvalid