Precise Segmentation for Children Handwriting Analysis by Combining Multiple Deep Models with Online Knowledge - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Precise Segmentation for Children Handwriting Analysis by Combining Multiple Deep Models with Online Knowledge

Simon Corbillé
  • Function : Author
  • PersonId : 1037773
Eric Anquetil
Elisa Fromont

Abstract

We present a strategy, called Seq2Seg, to reach both precise and accurate recognition and segmentation for children handwritten words. Reaching such high performance for both tasks is necessary to give personalized feedback to children who are learning how to write. The first contribution is to combine the predictions of an accurate Seq2Seq model with the predictions of a R-CNN object detector. The second one is to refine the bounding box predictions provided by the detector with a segmentation lattice computed from the online signal. An ablation study shows that both contributions are relevant, and their combination is efficient enough for immediate feedback and achieves state of the art results even compared to more informed systems.
Fichier principal
Vignette du fichier
ICDAR_2023_CameraReady_SimonCorbille.pdf (1.26 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04142592 , version 1 (27-06-2023)

Licence

Identifiers

  • HAL Id : hal-04142592 , version 1

Cite

Simon Corbillé, Eric Anquetil, Elisa Fromont. Precise Segmentation for Children Handwriting Analysis by Combining Multiple Deep Models with Online Knowledge. ICDAR 2023 - 17th International Conference on Document Analysis and Recognition, Aug 2023, San José, United States. pp.1-18. ⟨hal-04142592⟩
50 View
112 Download

Share

Gmail Mastodon Facebook X LinkedIn More