NewCheck Out Release 1.7.2 With Magic Wand 🪄
Back to integrations

Bounding Box OCR


Tesseract is one of the oldest and most widely used open source Optical Character Recognition (OCR) libraries. Label Studio can use Tesseract to apply bounding box OCR labeling to images through its machine learning interface.


Integrating Tesseract with Label Studio provides the following benefits:

  • Automated Labeling: Tesseract speeds up OCR labeling process by automatically applying bounding box labels to text.
  • Interactive Labeling: Labelers select target text which is automatically labeled by OCR, targeting only the portions of a document that a labeler chooses.
  • High-Quality Labels: With over 30 years of active development, Tesseract is one of the most well-understood and tested OCR libraries.

Related Integrations

Scikit Learn

Machine learning toolkit


Library to enable Bayesian active learning


Named entity recognition


Open source machine learning framework