We present a framework to generate synthetic historical documents with precise ground truth
using nothing more than a collection of unlabeled historical images. Obtaining large labeled …

Abstract Developing an Optical Character Recognition (OCR) system for handwritten texts is
a challenging research problem. Handwritten text can be largely different even for the same …

In this paper, we propose a novel method for handwritten text generation that uses a style
encoder based on a vision transformer network that encodes handwriting style from …

Constructing a highly accurate handwritten OCR system requires large amounts of
representative training data, which is both time-consuming and expensive to collect. To …

Deep document enhancement models often suffer in real world applications due to limited
annotation and bias in training data. Moreover, generative models are often prone to …

While existing neural network-based approaches have shown promising results in
Handwritten Text Recognition (HTR) for high-resource languages and …

Images of historical Vietnamese steles allow historians to discover invaluable information
regarding the past of the country, especially about the life of people in rural villages. Due to …

Style-guided text image generation tries to synthesize text image by imitating reference
image's appearance while keeping text content unaltered. The text image appearance …

This study is dedicated to enhancing the effectiveness of Optical Character Recognition
(OCR) systems, with a special emphasis on Arabic handwritten digit recognition. The choice …

Lecture videos have become a great resource for students and teachers. These videos are a
vast information source, but most search engines only index them by their audio. To make …