A Dataset of Inertial Measurement Units for Handwritten English Alphabets

Hari Prabhat Gupta, Rahul Mishra
7/5/2023
cs.CV

No official code found. Best implementation: DevanshMittal96/EdgeWrite (0 stars, MIT, last commit 2026-04-13).

Abstract

This paper presents an end-to-end methodology for collecting datasets to recognize handwritten English alphabets by utilizing Inertial Measurement Units (IMUs) and leveraging the diversity present in the Indian writing style. The IMUs are utilized to capture the dynamic movement patterns associated with handwriting, enabling more accurate recognition of alphabets. The Indian context introduces various challenges due to the heterogeneity in writing styles across different regions and languages. By leveraging this diversity, the collected dataset and the collection system aim to achieve higher recognition accuracy. Some preliminary experimental results demonstrate the effectiveness of the dataset in accurately recognizing handwritten English alphabet in the Indian context. This research can be extended and contributes to the field of pattern recognition and offers valuable insights for developing improved systems for handwriting recognition, particularly in diverse linguistic and cultural contexts.

View on arXivView PDF

Code Implementations(1)

DevanshMittal96/EdgeWriteCommunity63%
MIT

Lightweight 52-class IMU handwriting recognition for memory-constrained microcontrollers. First systematic benchmark on the IIT BHU IMU Alphabet Dataset (arXiv:2307.02480). Includes a custom TCN achieving 86.31% case-insensitive accuracy in a 145 KB INT8 payload, and documents the physical case-sensitivity barrier in IMU-only kinematics.

00C++, PythonApr 13, 20266 months agoMIT

Similar Papers

BeHGAN: Bengali Handwritten Word Generation from Plain Text Using Generative Adversarial Networks

85% match2025

Handwritten Word Recognition using Deep Learning Approach: A Novel Way of Generating Handwritten Words

83% match2023

PLATTER: A Page-Level Handwritten Text Recognition System for Indic Scripts

83% match2025

Contrastive Masked Autoencoders for Character-Level Open-Set Writer Identification

83% match2025

Learning based Ge'ez character handwritten recognition

83% match2024

HATFormer: Historic Handwritten Arabic Text Recognition with Transformers

82% match2024

Cite this paper

@article{gupta2023dataset,
  title  = {A Dataset of Inertial Measurement Units for Handwritten English Alphabets},
  author = {Hari Prabhat Gupta and Rahul Mishra},
  year   = {2023},
  eprint = {2307.02480},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.02480v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.02480.svg)](https://codeofpaper.com/paper/2307.02480)

Discussion