What's new

This topic contains information about the new features and enhancements included with Kofax OmniPage Capture SDK 22.1.0.

PDF/A-4 format support

Capture SDK now supports the following PDF/A-4 formats:

  • PDF/A-4
  • PDF/A-4e
  • PDF/A-4f

Multi-threading support for Asian OCR

Added multi-threading support for the Asian OCR engine to gain performance. On capable hardware, the improvement affects the following languages:

  • Simplified Chinese

  • Traditional Chinese

  • Japanese

  • Korean

  • Arabic

Improved mixed Arabic-English OCR accuracy

CSDK now applies English recognition on Arabic zones to look for English text embedded in the Arabic. With this method, CSDK can effectively locate English text within the Arabic text in great detail: English areas may cover a section, a sentence, or even just a word. Using the appropriate recognition engine per language provides more accurate recognition results.

Eliminated Arabic OCR accuracy gap

CSDK now meets the competitor's OCR accuracy result in Arabic.

Improved OCR accuracy of Eastern-Arabic numbers

Now the Arabic engine in CSDK is better tuned for recognizing Eastern-Arabic numerals.

Improved Hebrew OCR accuracy

CSDK now runs Hebrew OCR with improved accuracy, and it has no disadvantage compared to its competitors.

Auto-rotation for Hebrew and Thai

CSDK is now able to detect the orientation of Hebrew and Thai pages and rotate as needed, resulting in better OCR accuracy in these languages.

Improved template-based form recognition

CSDK Form Template Editor now has improved recognition accuracy for IDs and passports due to supporting the following features:

  • Graphic zones, such as photos and signatures

  • Zone filters, such as numbers-only and upper-case characters

  • FilterPlus for improved handwriting recognition

Improved QR code recognition

CSDK now works with improved QR code detection and recognition.

Code 32 barcode support

CSDK now supports Code 32 barcodes, the standard commissioned by the Italian Health Ministry. Code 32 is also called:

  • IMH

  • Italian Pharmacode

  • Radix 32 Barcode

Support hOCR and ALTO Output Standards

CSDK now support the hOCR and ALTO open standards in the Direct TXT module to output OCR results. Refer to the online help for details.

Customizable output page size

Earlier versions of CSDK calculated the output page size based on the input image dimensions. CSDK now allows customers to specify the page size for the output file (DOCX).