Hancom Releases Open Source PDF Accessibility Conversion Feature

Hancom has released as open source an artificial intelligence (AI)-based feature that enables bulk conversion of PDFs into accessible documents for free.

On April 30, Hancom distributed a version of OpenDataLoader PDF equipped with an automatic accessibility tag generation and insertion feature. This allows companies and public institutions to convert large quantities of PDFs into accessible documents without any additional costs or fees.

A significant portion of PDF documents lack accessibility tags, making it difficult for those in information accessibility-vulnerable groups to understand the content. This is because screen reader programs are unable to properly recognize the document structure.

This new feature operates by having AI analyze the document structure and directly write the results into the original PDF file. The AI distinguishes elements such as headings, tables, lists, and images, and incorporates them as tags within the PDF in accordance with accessibility structures.

OpenDataLoader PDF can be used without any restriction on the number of documents and processes everything within the internal environment, ensuring that sensitive documents are not transmitted to external servers. Libraries for Python, Node.js, and Java, as well as command-line tools, are also provided, allowing integration with existing workflows.

Hancom is positioning this release not just as a simple feature distribution, but as part of its document AI platform strategy, which goes beyond document processing tools to encompass accessibility compliance and regulatory adherence. Hancom generates tag structures based on the PDF Association's technical specifications and the international PDF Universal Accessibility (PDF/UA) standard. The company is also working with Dual Lab, the developer of the VeraPDF accessibility verification tool, to enhance its quality verification system.

Hancom plans to launch a commercial solution within the second quarter of this year that can output results compliant with the PDF/UA international standard. Under its 'open core' strategy, Hancom will offer broad access as open source and provide specialized solutions to corporate clients who require audit response and regulatory compliance.

Hancom Chief Technology Officer (CTO) Jeong Ji-hwan said, "The PDF accessibility market has long been characterized by high costs and complex implementation structures," adding, "By releasing core features as open source, Hancom aims to enable anyone to begin accessibility conversion without cost burdens."

This content was produced with the assistance of AI translation services.