Hi everyone,

It's almost the end of the year! And what a year! 🙂

You will find below the overview of what we’ve done and improved in the GdPicture.NET & DocuVieware SDKs this month.

We've also published the first 3 articles of our Table Extraction Series on our blog:

In Part 4 of the Series, we'll discuss our upcoming feature, Table Conversion to Excel.
Stay tuned!

We discussed how AI-based Intelligent Document Processing features such as key-value pair extraction, table extraction, and smart redaction can help with various PDF and electronic document challenges.

If you missed it, you can watch the recording by clicking the link below.

Watch the recording 

Improved PDF rendering engine.
Improved PDF/A conversion engine.
Improved PDF parsing of malformed documents.
Fixed PDF OCG print and export states handling.
Improved PDF digital signature memory management for large documents.

OCR
Improved OCR engine accuracy.

Improved PDF text extraction engine.

Improved Smart Redaction engine accuracy.
Improved KVP engine accuracy.
Improved table processing accuracy.

New RedactVehiculeIdentificationNumbers property in the SmartRedactionOptions class.
New Vehicle Identification Number (VIN) member in the DataType enumeration.

Improved PPT and PPTX rendering engine.
Improved metafile rendering on *.API assemblies for Office formats.
Fixed an issue that prevented EML from being rendered on *.API assemblies.

Extracting tables from PDFs and electronic documents can be complex, depending on the nature of the file. In this series, we’ll see how automatic table extraction can help you. 

In this second article of our Table Extraction series, we will see how to apply deep learning approaches to detect tables and decode them on document images.

In this third article, we’ll see how the GdPicture.NET engine goes beyond OCR and Deep Learning methods thanks to the Layout Understanding approach.