This is documentation for Mathematica 8, which was
based on an earlier version of the Wolfram Language.
View current documentation (Version 11.1)


recognizes text in image and returns it as a string.
  • TextRecognize works with arbitrary grayscale and multichannel images, operating on the intensity value of each pixel.
  • TextRecognize by default assumes that text to be recognized is in English. When working with other languages, better results may be obtained by setting the Language option to one of the following: , , , , , .
Recognize arbitrary text:
White text on a dark background:
Slightly rotated text:
Color image:
Two columns:
Read a German poem:
Recognize Russian text:
Recognize warped Russian text:
Fonts smaller than a certain size cannot be recognized:
When recognizing formatted numbers, whitespace may cause OCR errors:
Read from a book cover:
New in 8