Vision Models
Last updated
Last updated
Our API enables you to use machine learning models for tasks that require visual capabilities. These models are referred to as vision models. Within our API, we offer two categories of vision models: OCR and OFR.
With OCR technology, you can analyze any document and extract text as well as other characters and symbols. This allows you to detect:
Text
Paragraph blocks
Handwriting
Text inside PDF/TIFF files
In contrast to OCR, OFR allows you to analyze not just documents but also images. You can filter exactly what you want to find in the image by the features they include:
Crop hints
Faces
Image properties
Labels
Landmarks
Logos
Multiple objects
Explicit content
Web entities and pages
And many more