Handwriting Styles: Benchmarks and Evaluation Metrics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Handwriting Styles: Benchmarks and Evaluation Metrics

Résumé

Extracting styles of handwriting is a challenging problem, since the style themselves are not well defined. It is a key component to develop systems with more personalized experiences for humans. In this paper, we propose baseline benchmarks, in order to set anchors to estimate the relative quality of different handwriting style methods. This will be done using deep learning techniques, which have shown remarkable results in different machine learning tasks, learning classification, regression, and most relevant to our work, generating temporal sequences. We discuss the challenges associated with evaluating our methods, which is related to evaluation of generative models in general. We then propose evaluation metrics, which we find relevant to this problem, and we discuss how we evaluate the performance metrics. In this study, we use IRON-OFF dataset [1]. To the best of our knowledge, no existing benchmarks or evaluation metrics for this task exit yet, and this dataset has not been used before in the context of handwriting synthesis.
Fichier principal
Vignette du fichier
pellier18d.pdf (925.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01900765 , version 1 (22-10-2018)

Identifiants

  • HAL Id : hal-01900765 , version 1

Citer

Omar Mohammed, Gérard Bailly, Damien Pellier. Handwriting Styles: Benchmarks and Evaluation Metrics. IEEE International Workshop on Deep and Transfer Learning (DTL 2018), Oct 2018, Valencia, Spain. ⟨hal-01900765⟩
75 Consultations
146 Téléchargements

Partager

Gmail Facebook X LinkedIn More