Document Filters 25.3 Release
Every document hides more insight than what first meets the eye. Screenshots and diagrams often lock away critical text, healthcare records carry complex structures, and tables can be deceptively hard to detect. With Document Filters 25.3, these blind spots are brought into the open. This release adds OCR for embedded images, HL7 medical record processing with preserved structure, and smarter table detection in PDFs. Together these advances capture more context earlier, reduce manual cleanup, and deliver higher-quality inputs for AI and analytics.
Watch as we walk through a few of the new features in the 25.3 release of Document Filters.
OCR of Embedded Images in Text Documents
Many documents include inline visuals, such as screenshots, diagrams, or scans, that contain meaningful text. Document Filters can now recognize that text during processing and place it back into the output at the correct position. The result is richer Markdown and HD output that maintains context and continuity, improving downstream search, RAG, and transformation workflows.
Use the OCR_INLINE_IMAGES processing option to enable this functionality, while using the custom OCR integration to utilize any text extraction product, whether that's an OCR engine or AI model.
HL7 Medical Record Processing
Document Filters now detects and processes HL7 medical records into structured, machine-readable output. Segment order and field groupings are preserved in Markdown and HD so clinical data keeps its original shape, making it easier to integrate with analytics, interoperability, and AI initiatives.
A standard HL7 v2 message.
Document Filters text-mode markdown conversion is HL7 aware, and converts HL7 into a useful and easy to understand format for AI and other downstream systems.
In addition to text-mode markdown, HL7 messages can also be converted into any of the Document Filters HD outputs to be able to easily display in a viewer.
Improved Detection for Inner-Border Tables in PDFs
PDFs often present tables with only internal cell lines and no outer frame. Document Filters's PDF table detection now identifies these tables more reliably, improving the completeness and accuracy of table extraction for AI, analytics, and document transformation.
Release Links
- Document Filters 25.3 Release Notes
- Document Filters 25.3 Software Bill of Materials
- Enhancement Requests