HANCOM has open-sourced a feature that automatically generates and inserts accessibility tags for PDF documents.
HANCOM said on the 30th that it released the feature built into OpenDataLoader PDF. The feature works by having artificial intelligence (AI) analyze a document's structure and then write the results directly inside the original PDF file. It distinguishes components such as titles, tables, lists, and images and reflects them inside the PDF in the form of tags that incorporate the accessibility structure, and it is notable for offering for free even the stage where the extraction results are reflected in the actual PDF in a complete form.
PDF is one of the most widely used digital document formats worldwide, but a large share of documents have circulated without accessibility tags. In such cases, screen readers (text-to-speech programs) cannot properly recognize the document structure, making it hard for people with visual impairments and other groups with limited access to information to understand the content.
This demand is expanding quickly in step with regulatory changes. The main obligations under the U.S. ADA (Americans with Disabilities Act) Title II begin to apply starting in Apr. 2026, and with the European EAA (European Accessibility Act) and Korea's Act on the Prohibition of Discrimination against Persons with Disabilities also aligning, demand from corporations and public institutions to convert PDFs for accessibility is surging.
In the existing market, the free tier for cloud API offerings was limited to only dozens of pages per month, and full-scale adoption incurred annual corporate license expense in the tens of thousands of dollars. Some desktop products inserted watermarks in outputs even during free trials or restricted key features behind separate paid tiers.
By contrast, OpenDataLoader PDF can be used without limits on the number of documents. It is also processed in an on-premise environment, so sensitive documents are not sent to external servers. Python, Node.js, and Java libraries and a command-line tool are provided to integrate with existing workflows.
HANCOM is pursuing this release as part of a document AI platform strategy that goes beyond document processing tools to encompass accessibility readiness and regulatory compliance. HANCOM generates tag structures based on the PDF Association technical specifications and the PDF/UA (PDF Universal Accessibility) international standard, and is enhancing its quality verification system in collaboration with Dual Lab, the team behind the PDF accessibility validation tool "veraPDF."
HANCOM plans to launch a commercial solution by the second quarter of 2026 that outputs results compliant with the PDF/UA international standard. The core features will be offered as open source, and specialized solutions will be provided to corporate customers that need to respond to audits and comply with regulations.
Jung Ji-hwan, HANCOM chief technology officer (CTO), said, "HANCOM aims to open-source core features so anyone can start accessibility conversion without expense burdens," and added, "For corporations that need to convert large volumes of documents, we will provide free core tools alongside commercial solutions compliant with PDF/UA."