Document Recognition in the Cultural Heritage: Methods and Applications

The field of document recognition in the cultural heritage is rapidly progressing, wherein vast amounts of ancient manuscripts in libraries and other institutions across the world are increasingly undergoing digitization and transcription. However, the automatic recognition of patterns in ancient manuscripts to render them readable, searchable and understandable remains a challenging task. This can be due to degradations including ink bleed-through, ink corrosion, stains on paper or parchment, difficulty in the character discrimination, elements different from the text, such as images, etc. that limit the effectiveness of existing techniques. In recent times, machine learning, and deep learning-based methods in particular, have achieved significant performance improvements in document recognition. The aim of this Special Issue is to present recent advances in methods and applications for document recognition in the cultural heritage, attracting research papers from a wide array of disciplines, including machine learning, pattern recognition, image analysis, and digital humanities. The focus is to highlight advances in the research topics representing document recognition from a broad perspective, and to promote new algorithms and methodologies for better reflection of the state-of-the-art in this field.

We are interested in original research that addresses the various issues in document recognition. Topics include, but are not limited to, the following:

Handwritten document analysis;

 

Writer recognition;

Text line extraction or segmentation;

Document image binarization;

Background noise removal;

Word spotting;

Word recognition;

Automatic recognition and transcription of manuscripts;

Active learning for handwritten text recognition;

Scribe identification;

Dating of historical manuscripts;

Document layout analysis;  

Human–document interaction;

Feature extraction and representation;

Digital humanities applications;

Image processing, classification, and retrieval.