handwritten-text-recognition

Handwritten Document Recognition

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in handwritten-text-recognition

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find handwritten-text-recognition models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

DAN: A Segmentation-Free Document Attention Network for Handwritten Document Recognition

Denis Coquenet, Clément Chatelain, T. Paquet•Tue Mar 22 2022

This work proposes an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network, made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process.

77

Content

0

Paper Graph

Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition

Denis Coquenet, Clément Chatelain, T. Paquet•Tue Jan 24 2023

Faster DAN is proposed, a two-step strategy to speed up the recognition process at prediction time: the model predicts the first character of each text line in the document, and then completes all the text lines in parallel through multi-target queries and a specific document positional encoding scheme.

11 0

Paper Graph

Towards End-to-end Handwritten Document Recognition

Denis Coquenet•Thu Sep 29 2022

This thesis proposed the first end-to-end approach dedicated to the recognition of both text and layout, at document level, based on a fully convolutional network, in order to design a first generic feature extraction step for the handwriting recognition task.

1 0

Paper Graph

Adding a benchmark result helps the community track progress.