Few shots are all you need
Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. In this paper, we propose a few-shot learning-based handwriting recognition approach that significantly reduces the human annotation process, by requiring only a few images of e...
| Autores: | , , , |
|---|---|
| Formato: | artículo |
| Fecha de publicación: | 2022 |
| País: | España |
| Recursos: | Universitat Autònoma de Barcelona |
| Repositorio: | Dipòsit Digital de Documents de la UAB |
| Idioma: | inglés |
| OAI Identifier: | oai:ddd.uab.cat:264402 |
| Acesso em linha: | https://ddd.uab.cat/record/264402 https://dx.doi.org/urn:doi:10.1016/j.patrec.2022.06.003 |
| Access Level: | acceso abierto |
| Palavra-chave: | Handwritten text recognition Few-shot learning Unsupervised progressive learning Ciphered manuscripts |
| Resumo: | Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. In this paper, we propose a few-shot learning-based handwriting recognition approach that significantly reduces the human annotation process, by requiring only a few images of each alphabet symbols. The method consists of detecting all the symbols of a given alphabet in a textline image and decoding the obtained similarity scores to the final sequence of transcribed symbols. Our model is first pretrained on synthetic line images generated from an alphabet, which could differ from the alphabet of the target domain. A second training step is then applied to reduce the gap between the source and the target data. Since this retraining would require annotation of thousands of handwritten symbols together with their bounding boxes, we propose to avoid such human effort through an unsupervised progressive learning approach that automatically assigns pseudo-labels to the unlabeled data. The evaluation on different datasets shows that our model can lead to competitive results with a significant reduction in human effort. The code will be publicly available in the following repository: https://github.com/dali92002/HTRbyMatching. |
|---|