Graph Neural Network based Handwritten Trajectories Recognition

TL;DR

The paper addresses handwritten trajectory recognition by converting handwriting into graphs via chain-code features and applying Graph Neural Networks (GNNs) to perform recognition on both offline and online data. It introduces drawing-order recovery for offline handwriting to obtain chain-code graphs and evaluates a range of GNN operators on MNIST, UNIPEN, and GHWT datasets. Key contributions include the first integration of chain-code based trajectory features with GNNs for HWR, systematic comparison of multiple GNN operators, and demonstration of strong performance with batch-based training. The results suggest a graph-based trajectory representation is effective for HWR and offers a scalable approach with potential extensions to other trajectory-related domains.

Abstract

The graph neural networks has been proved to be an efficient machine learning technique in real life applications. The handwritten recognition is one of the useful area in real life use where both offline and online handwriting recognition are required. The chain code as feature extraction technique has shown significant results in literature and we have been able to use chain codes with graph neural networks. To the best of our knowledge, this work presents first time a novel combination of handwritten trajectories features as chain codes and graph neural networks together. The handwritten trajectories for offline handwritten text has been evaluated using recovery of drawing order, whereas online handwritten trajectories are directly used with chain codes. Our results prove that present combination surpass previous results and minimize error rate in few epochs only.

Figures (2)

• Figure 1: GNN based Dataset formation
• Figure 2: GNN training