Applications
Optical Character Recognition
OCRConverting images of text, like scanned documents or photos, into machine-readable, editable text.
OCR reads text out of images, turning a scanned page, receipt, or street sign into characters software can search and edit. It is a mature technology that has become far more accurate with deep learning, now handling messy handwriting, odd fonts, and photos taken at an angle. It is a workhorse behind document digitization, data entry automation, and accessibility.
Reference: Wikipedia: Optical Character Recognition
Related terms
Computer Vision
The field of AI that lets computers interpret images and video, from recognizing objects to reading documents.
Convolutional Neural Network
A network design built for images, which scans for small visual patterns and builds them up into recognizable objects.
Natural Language Processing
The field of AI focused on getting computers to understand and generate human language.