AI engineering glossary · Computer vision
What is text recognition?
Text recognition: The stage of OCR that reads the characters in a cropped text region and outputs a string. Modern systems use a CNN or transformer encoder with a sequence decoder. It must cope with fonts, blur, skew and different lengths of text.
Text recognition: an example
A cropped image of a licence plate is turned into the string 'KA05MN1234'.
Related terms
More Computer vision terms
- Thresholding
- Top-k accuracy
- Translation invariance
- Transposed convolution
- Two-stage detector
- U-Net
- Upsampling
- VGG
Where you learn it
Text recognition is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.