Adaptive binarisation is a very important part of ABBYY's image pre-processing. In V10 technologies the technologies were improved to deliver better source images for the character recognizers and to persevere more text on images, but also to remove “noise” that is only shine trough text from the other side of the document page.

• Bookscanners often use hard light and after binarization this can result in “host text-lines” without any useful information
• The ABBYY's improved binarization technology is able to detect that and remove the “garbage” before applying text recognition

The optimized binarization was introduced in V10 technologies :

• FineReader Engine 10 Win (10/2010)
• FlexiCapture Engine 10 (10/2012)

• Binarization and Background Filtering
• Image Preprocessing and Binarisation for Camera OCR

Back to: Inside OCR Overview