Towards Writing Style Adaptation in Handwriting Recognition

conference paper

English

One of the challenges of handwriting recognition is to transcribe a large number of vastly different writing styles. State-of-the-art approaches do not explicitly use information about the writer's style, which may be limiting overall accuracy due to various ambiguities. We explore models with writer-dependent parameters which take the writer's identity as an additional input. The proposed models can be trained on datasets with partitions likely written by a single author (e.g. single letter, diary, or chronicle). We propose a Writer Style Block (WSB), an adaptive instance normalization layer conditioned on learned embeddings of the partitions. We experimented with various placements and settings of WSB and contrastively pre-trained embeddings. We show that our approach outperforms a baseline with no WSB in a writer-dependent scenario and that it is possible to estimate embeddings for new writers. However, domain adaptation using simple finetuning in a writer-independent setting provides superior accuracy at a similar computational cost. The proposed approach should be further investigated in terms of training stability and embedding regularization to overcome such a baseline.

Handwritten text recognition, OCR, Domain adaptation, Domain dependent parameters, Finetuning, CTC.

KOHÚT, J.; HRADIŠ, M.; KIŠŠ, M.

19. 8. 2023

Springer Nature Switzerland AG

San José

978-3-031-41684-2

Document Analysis and Recognition - ICDAR 2023

Lecture Notes in Computer Science

0302-9743

Lecture Notes in Computer Science

14190

1

Federal Republic of Germany

377

394

18

https://pero.fit.vutbr.cz/publications