One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition

by   Mohamed Ali Souibgui, et al.

Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). This appears, for example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the content. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol from the desired alphabet. After generating symbols, we create synthetic lines to train state-of-the-art HTR architectures in a segmentation free fashion. Quantitative and qualitative analyses were carried out and confirm the effectiveness of the proposed method, achieving competitive results compared to the usage of real annotated data.


Few Shots Is All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwriting Recognition

Handwritten text recognition in low resource scenarios, such as manuscri...

A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition

Encoded (or ciphered) manuscripts are a special type of historical docum...

Content and Style Aware Generation of Text-line Images for Handwriting Recognition

Handwritten Text Recognition has achieved an impressive performance in p...

Dirichlet-Smoothed Word Embeddings for Low-Resource Settings

Nowadays, classical count-based word embeddings using positive pointwise...

Generating Synthetic Data for Text Recognition

Generating synthetic images is an art which emulates the natural process...

GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images

Although current image generation methods have reached impressive qualit...