Version 8.0 | Version 9.0 | Version 11 | |
---|---|---|---|
Recognition | |||
Image Input Formats | BMP, DCX, GIF, JPEG, PNG, TIFF, JPEG200, JBIG2 | New: WDP | |
PDF Import | yes, with intelligent automatic text layer control | ||
Texttypes | Normal, Matrix, Typewriter, OCR-A, OCR-B, CMC7, MICR | New: Receipts | |
1D barcodes | yes, 16 types | ||
2D barcodes | on request only | yes, PDF 417, Aztec, Data Matrix, QR Code. |
yes, extended with Maxi Code |
Recognition Languages supported in the core technology |
189 37 languages with dictionary support |
> 190 37 languages with dictionary support |
> 200 52 languages with dictionary support |
Chinese, Japanese, Korean OCR | – | only on request |
included in trial license extended language version available online |
Arabic OCR | – | – | |
Support for “old” fonts Gothic/Fraktur |
– | – | not included, for project requests contact ABBYY |
Processing | |||
Image Preprocessing | yes | slightly optimized | improved technology |
Camera OCR | – | 1st generation | 3rd generation |
Image Orientation Detection | yes | yes | yes |
Layout Analysis | yes, parameters for text, tables, barcodes, pictures | ||
Text Format Detection | yes, parameters for bold, italic, font size, color, more… | ||
Aggressive Text-Extraction | – | – | new |
Multi-Core Support | – | manual, own instance scalability processing | new, built in for multi-page documents |
Processing Profiles | – | – | new feature for different scenarios: conversion, text extraction, barcode recognition, etc. |
Export | |||
Text only | yes, full Unicode support | ||
Office Formats | RTF, DOC, XLS | RTF, DOC, XLS, PPT | RTF, ODT, DOCX, XLSX, PPTX (“DOC/PPT export” no longer supported) |
Web Formats | HTML | HTML + Images | HTML + Images + CSS |
eBook Formats | – | – | ePub, FB2 |
XML | – | ABBYY XML | ABBYY XML, new ALTO XML |
yes, image only, text only, text under image | |||
PDF Options | yes, security and encryption settings, print restrictions, tagged PDFs, recreation of hyperlinks | ||
PDF/A1 | – | yes | yes |
PDF/A2 | – | – | yes |
Highly compressed PDFs (MRC) | – | yes | yes, improved technology |
PDF Export Profiles | – | – | yes |
Operating System | |||
Architecture (bitness) | 32-bit | 32-bit | 64-bit |
glibc Version | glibc 2.3.2 | glibc version 2.5 and above | glibc version 2.11 and above |