Point to segment distance DTW for online handwriting signals matching - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Point to segment distance DTW for online handwriting signals matching

(1, 2, 3) , (3) , (1, 2)
1
2
3

Abstract

In this paper, we propose DTW seg , a modified DTW algorithm based on a point-to-segment distance instead of the euclidean point-to-point distance. Applying DTW seg to online handwriting matching proves to be advantageous compared to other algorithms as it is less sensitive to differences between signals sampling rates occurring due to acquisition frequencies or handwriting speed. It eliminates the need for a commonly practiced resampling that omits an important dynamic part of the ductus. Experiments on IRONOFF french words dataset and FLOWCHARTS dataset show DTW seg to be least impacted by sampling rate alterations. We also propose a new benchmark of state-of-the-art methods on offline handwriting to online conversion based on our new proposed metric.
Fichier principal
Vignette du fichier
main.pdf (5.19 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03914726 , version 1 (28-12-2022)

Identifiers

  • HAL Id : hal-03914726 , version 1

Cite

elmokhtar mohamed moussa, Thibault Lelore, Harold Mouchère. Point to segment distance DTW for online handwriting signals matching. ICPRAM 2023, Feb 2023, Lisbonne, Portugal. ⟨hal-03914726⟩
0 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More